indonesian_twitter_hate_speech_classification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMxGkDwCXg1RX4euR126N9/"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Indonesian Hate Speech Classification"
      ],
      "metadata": {
        "id": "Bh4nZmEMws8G"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Import Library"
      ],
      "metadata": {
        "id": "5cbO0Ru-wxn9"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "aZi7FPA5wpgB"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import numpy as np\n",
        "\n",
        "%matplotlib inline\n",
        "sns.set(style='darkgrid')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OhXJlHCUxbeP",
        "outputId": "8deba902-82dc-45b8-821f-963843a38695"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/gdrive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Load Dataset"
      ],
      "metadata": {
        "id": "2J2h-Ur1zOdb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "data = pd.read_csv('/content/gdrive/MyDrive/learn_monday/text_preprocessing/IDHSD_RIO_unbalanced_713_2017.txt', encoding='cp1252', sep='\\t', header=None, names=['label', 'tweet'], skiprows=1, engine='python')\n",
        "data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "03S-jwaUzhYZ",
        "outputId": "88dca65b-2b13-4a3b-ece9-6cd95c71e41e"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      label                                              tweet\n",
              "0    Non_HS  RT @spardaxyz: Fadli Zon Minta Mendagri Segera...\n",
              "1    Non_HS  RT @baguscondromowo: Mereka terus melukai aksi...\n",
              "2    Non_HS  Sylvi: bagaimana gurbernur melakukan kekerasan...\n",
              "3    Non_HS  Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...\n",
              "4    Non_HS  RT @lisdaulay28: Waspada KTP palsu.....kawal P...\n",
              "..      ...                                                ...\n",
              "708      HS  Muka Si BABi Ahok Tuh Yg Mirip SERBET Lantai.....\n",
              "709      HS  Betul bang hancurkan merka bang, musnahkan chi...\n",
              "710      HS  Sapa Yg bilang Ahok anti korupsi!?, klo grombo...\n",
              "711      HS  Gw juga ngimpi SENTILIN BIJI BABI AHOK, pcetar...\n",
              "712      HS  Mudah2an gw ketemu sama SI BABI IWAN BOPENG DI...\n",
              "\n",
              "[713 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-172a1e37-d236-4909-a4df-b4737a14af00\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>tweet</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @spardaxyz: Fadli Zon Minta Mendagri Segera...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @baguscondromowo: Mereka terus melukai aksi...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Sylvi: bagaimana gurbernur melakukan kekerasan...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @lisdaulay28: Waspada KTP palsu.....kawal P...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>708</th>\n",
              "      <td>HS</td>\n",
              "      <td>Muka Si BABi Ahok Tuh Yg Mirip SERBET Lantai.....</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>709</th>\n",
              "      <td>HS</td>\n",
              "      <td>Betul bang hancurkan merka bang, musnahkan chi...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>HS</td>\n",
              "      <td>Sapa Yg bilang Ahok anti korupsi!?, klo grombo...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>711</th>\n",
              "      <td>HS</td>\n",
              "      <td>Gw juga ngimpi SENTILIN BIJI BABI AHOK, pcetar...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>712</th>\n",
              "      <td>HS</td>\n",
              "      <td>Mudah2an gw ketemu sama SI BABI IWAN BOPENG DI...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>713 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-172a1e37-d236-4909-a4df-b4737a14af00')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-172a1e37-d236-4909-a4df-b4737a14af00 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-172a1e37-d236-4909-a4df-b4737a14af00');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Exploratory Data Analysis (EDA)"
      ],
      "metadata": {
        "id": "MRff7tPU1Dfa"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Fs844AGhz8nV",
        "outputId": "ec352793-fa39-474a-a459-4e78527aee51"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 713 entries, 0 to 712\n",
            "Data columns (total 2 columns):\n",
            " #   Column  Non-Null Count  Dtype \n",
            "---  ------  --------------  ----- \n",
            " 0   label   713 non-null    object\n",
            " 1   tweet   713 non-null    object\n",
            "dtypes: object(2)\n",
            "memory usage: 11.3+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "id": "Bbo8P6Msz8p-",
        "outputId": "deb3a2a2-641d-490c-dc9e-0e10d6297356"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         label                                              tweet\n",
              "count      713                                                713\n",
              "unique       2                                                703\n",
              "top     Non_HS  pertunjukan yang sangat membuat saya serius da...\n",
              "freq       453                                                  2"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-02ae7973-312a-4b78-b942-3612949e1ecd\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>tweet</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>713</td>\n",
              "      <td>713</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>2</td>\n",
              "      <td>703</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>pertunjukan yang sangat membuat saya serius da...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>453</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-02ae7973-312a-4b78-b942-3612949e1ecd')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-02ae7973-312a-4b78-b942-3612949e1ecd button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-02ae7973-312a-4b78-b942-3612949e1ecd');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.groupby('label').describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "id": "HEQcA48Hz8r8",
        "outputId": "668f4e64-a0b7-484e-c4a0-f2faff9e40db"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       tweet                                                               \n",
              "       count unique                                                top freq\n",
              "label                                                                      \n",
              "HS       260    259  Sini lu, kami enggak mau kampung kami didatang...    2\n",
              "Non_HS   453    444  Kenapa debat @MataNajwa ini, Ahok makin keliat...    2"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-95222b35-3a9b-4371-b6ce-b83d0fa1adf4\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr th {\n",
              "        text-align: left;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr:last-of-type th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th colspan=\"4\" halign=\"left\">tweet</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th>count</th>\n",
              "      <th>unique</th>\n",
              "      <th>top</th>\n",
              "      <th>freq</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>label</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>HS</th>\n",
              "      <td>260</td>\n",
              "      <td>259</td>\n",
              "      <td>Sini lu, kami enggak mau kampung kami didatang...</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Non_HS</th>\n",
              "      <td>453</td>\n",
              "      <td>444</td>\n",
              "      <td>Kenapa debat @MataNajwa ini, Ahok makin keliat...</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-95222b35-3a9b-4371-b6ce-b83d0fa1adf4')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-95222b35-3a9b-4371-b6ce-b83d0fa1adf4 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-95222b35-3a9b-4371-b6ce-b83d0fa1adf4');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data['length'] = data['tweet'].apply(len)"
      ],
      "metadata": {
        "id": "PkavgSG_z8uf"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data.hist(column = 'length',\n",
        "          by = 'label',\n",
        "          bins = 50,\n",
        "          figsize = (12,4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 345
        },
        "id": "6yIHk76K1y__",
        "outputId": "811c804e-0e02-4032-9d77-15271b16fd70"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([<matplotlib.axes._subplots.AxesSubplot object at 0x7f5dd3631810>,\n",
              "       <matplotlib.axes._subplots.AxesSubplot object at 0x7f5dbce54550>],\n",
              "      dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 8
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 864x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig1 = sns.barplot(x = 'label',\n",
        "                   y = 'length',\n",
        "                   data = data)\n",
        "plt.title('Average Word Length vs Label')\n",
        "plot = fig1.get_figure()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 302
        },
        "id": "-bnyHb4118B2",
        "outputId": "42944823-7bfb-4da9-f7b1-4f31d03ba667"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig2 = sns.countplot(x= 'label',\n",
        "                     data = data)\n",
        "plt.title('Label Counts')\n",
        "plot = fig2.get_figure()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 302
        },
        "id": "mfHRnsty2xgO",
        "outputId": "79290804-37d9-4532-9855-9cf2b6dc1ed0"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Jumlah tweet yang termasuk kategori Non-Hate Speech lebih banyak daripada yang masuk ke dalam kategori Hate Speech."
      ],
      "metadata": {
        "id": "-czGAMf-29u1"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Text Preprocessing"
      ],
      "metadata": {
        "id": "yawboF5C2_kt"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 1. Over-Sampling Minority Class"
      ],
      "metadata": {
        "id": "WfugoSMv3FMX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "count_class_NONHS, count_class_HS = data.label.value_counts()"
      ],
      "metadata": {
        "id": "RoZWnI3P27Ru"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "count_class_NONHS"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r6isqVK43SXV",
        "outputId": "2af3e2a4-a553-4736-ce29-51f46d2d111b"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "453"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "count_class_HS"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YxP9ESyP3ksU",
        "outputId": "803a65ce-114b-4215-8f60-e97fbbea8785"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "260"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_class_NONHS = data[data['label'] == 'Non_HS']\n",
        "data_class_HS = data[data['label'] == 'HS']"
      ],
      "metadata": {
        "id": "Td5AcWLp3mrk"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_class_NONHS"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "cxzo_mID3mtw",
        "outputId": "5fc45d8c-10bd-43eb-cd9c-3a2ce89fb794"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      label                                              tweet  length\n",
              "0    Non_HS  RT @spardaxyz: Fadli Zon Minta Mendagri Segera...     110\n",
              "1    Non_HS  RT @baguscondromowo: Mereka terus melukai aksi...     108\n",
              "2    Non_HS  Sylvi: bagaimana gurbernur melakukan kekerasan...     116\n",
              "3    Non_HS  Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...     115\n",
              "4    Non_HS  RT @lisdaulay28: Waspada KTP palsu.....kawal P...      79\n",
              "..      ...                                                ...     ...\n",
              "448  Non_HS       Dalam nama Tuhan Untuk jakarta yg lebih baik      44\n",
              "449  Non_HS  semagat buat pak Anies semoga selalu dalam rah...      59\n",
              "450  Non_HS  semua warga DKI gunakan hak pilihmu....jangan ...     102\n",
              "451  Non_HS  semoga Tuhan memberikan seluruh masyarakat DKI...     107\n",
              "452  Non_HS  Eks Pendukung Agus-Sylvi di Jakarta Timur Dekl...      81\n",
              "\n",
              "[453 rows x 3 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7b3846ca-bbc6-4730-896e-0b6e97e1eb9c\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>tweet</th>\n",
              "      <th>length</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @spardaxyz: Fadli Zon Minta Mendagri Segera...</td>\n",
              "      <td>110</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @baguscondromowo: Mereka terus melukai aksi...</td>\n",
              "      <td>108</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Sylvi: bagaimana gurbernur melakukan kekerasan...</td>\n",
              "      <td>116</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...</td>\n",
              "      <td>115</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @lisdaulay28: Waspada KTP palsu.....kawal P...</td>\n",
              "      <td>79</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>448</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Dalam nama Tuhan Untuk jakarta yg lebih baik</td>\n",
              "      <td>44</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>449</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>semagat buat pak Anies semoga selalu dalam rah...</td>\n",
              "      <td>59</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>450</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>semua warga DKI gunakan hak pilihmu....jangan ...</td>\n",
              "      <td>102</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>451</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>semoga Tuhan memberikan seluruh masyarakat DKI...</td>\n",
              "      <td>107</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>452</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Eks Pendukung Agus-Sylvi di Jakarta Timur Dekl...</td>\n",
              "      <td>81</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>453 rows × 3 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7b3846ca-bbc6-4730-896e-0b6e97e1eb9c')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-7b3846ca-bbc6-4730-896e-0b6e97e1eb9c button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-7b3846ca-bbc6-4730-896e-0b6e97e1eb9c');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_class_HS"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "AU2Q6P2-3mwj",
        "outputId": "73ea08d1-0411-41a8-92c1-e67f4fdeb53a"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    label                                              tweet  length\n",
              "453    HS  Ini pasti salah Jokowi, Ahok dan kafir-kafir a...      78\n",
              "454    HS  @fahmiabuazzam1 biar aja biar tai nya kena bap...     138\n",
              "455    HS  RT @BungWinar: Angin memporakporandakan basis ...     124\n",
              "456    HS  RT @Lupuz0503: Prestasi Ahok, \\nSelain mjadi m...     131\n",
              "457    HS  Ulama Kompak Nyatakan #HaramPemimpinKafir Pili...      62\n",
              "..    ...                                                ...     ...\n",
              "708    HS  Muka Si BABi Ahok Tuh Yg Mirip SERBET Lantai.....      62\n",
              "709    HS  Betul bang hancurkan merka bang, musnahkan chi...     107\n",
              "710    HS  Sapa Yg bilang Ahok anti korupsi!?, klo grombo...     139\n",
              "711    HS  Gw juga ngimpi SENTILIN BIJI BABI AHOK, pcetar...     137\n",
              "712    HS  Mudah2an gw ketemu sama SI BABI IWAN BOPENG DI...      66\n",
              "\n",
              "[260 rows x 3 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1e2fa716-9ce2-4ec3-873d-ca292928432e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>tweet</th>\n",
              "      <th>length</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>453</th>\n",
              "      <td>HS</td>\n",
              "      <td>Ini pasti salah Jokowi, Ahok dan kafir-kafir a...</td>\n",
              "      <td>78</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>454</th>\n",
              "      <td>HS</td>\n",
              "      <td>@fahmiabuazzam1 biar aja biar tai nya kena bap...</td>\n",
              "      <td>138</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>455</th>\n",
              "      <td>HS</td>\n",
              "      <td>RT @BungWinar: Angin memporakporandakan basis ...</td>\n",
              "      <td>124</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>456</th>\n",
              "      <td>HS</td>\n",
              "      <td>RT @Lupuz0503: Prestasi Ahok, \\nSelain mjadi m...</td>\n",
              "      <td>131</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>457</th>\n",
              "      <td>HS</td>\n",
              "      <td>Ulama Kompak Nyatakan #HaramPemimpinKafir Pili...</td>\n",
              "      <td>62</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>708</th>\n",
              "      <td>HS</td>\n",
              "      <td>Muka Si BABi Ahok Tuh Yg Mirip SERBET Lantai.....</td>\n",
              "      <td>62</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>709</th>\n",
              "      <td>HS</td>\n",
              "      <td>Betul bang hancurkan merka bang, musnahkan chi...</td>\n",
              "      <td>107</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>HS</td>\n",
              "      <td>Sapa Yg bilang Ahok anti korupsi!?, klo grombo...</td>\n",
              "      <td>139</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>711</th>\n",
              "      <td>HS</td>\n",
              "      <td>Gw juga ngimpi SENTILIN BIJI BABI AHOK, pcetar...</td>\n",
              "      <td>137</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>712</th>\n",
              "      <td>HS</td>\n",
              "      <td>Mudah2an gw ketemu sama SI BABI IWAN BOPENG DI...</td>\n",
              "      <td>66</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>260 rows × 3 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1e2fa716-9ce2-4ec3-873d-ca292928432e')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-1e2fa716-9ce2-4ec3-873d-ca292928432e button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-1e2fa716-9ce2-4ec3-873d-ca292928432e');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Oversampling data HS\n",
        "data_class_HS_over = data_class_HS.sample(count_class_NONHS,\n",
        "                                          replace = True)\n",
        "data_test_over = pd.concat([data_class_NONHS,\n",
        "                            data_class_HS_over], axis = 0)\n",
        "\n",
        "print('Random over-sampling:')\n",
        "print(data_test_over.label.value_counts())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6iJVine_3mzX",
        "outputId": "b80bf120-6d4d-433b-8829-a5bc0760c7f7"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Random over-sampling:\n",
            "Non_HS    453\n",
            "HS        453\n",
            "Name: label, dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig3 = sns.countplot(x = 'label',\n",
        "                     data = data_test_over)\n",
        "plt.title('Label Counts')\n",
        "plot = fig3.get_figure()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 302
        },
        "id": "ggwSYT2P4mdF",
        "outputId": "98ee11e6-c4bf-4859-8d28-ad454d0251d0"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_test_over.groupby('label').describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "id": "nRO6CfA541zW",
        "outputId": "929de382-57b0-4be2-8a0e-a37dea5ba1bf"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       length                                                        \n",
              "        count        mean        std   min   25%    50%    75%    max\n",
              "label                                                                \n",
              "HS      453.0  104.814570  29.440521  33.0  86.0  108.0  131.0  156.0\n",
              "Non_HS  453.0   97.494481  29.750780  18.0  75.0  100.0  122.0  164.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-2e3ff57f-58f3-4489-b757-cc283ed43ec4\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr th {\n",
              "        text-align: left;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr:last-of-type th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th colspan=\"8\" halign=\"left\">length</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>label</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>HS</th>\n",
              "      <td>453.0</td>\n",
              "      <td>104.814570</td>\n",
              "      <td>29.440521</td>\n",
              "      <td>33.0</td>\n",
              "      <td>86.0</td>\n",
              "      <td>108.0</td>\n",
              "      <td>131.0</td>\n",
              "      <td>156.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Non_HS</th>\n",
              "      <td>453.0</td>\n",
              "      <td>97.494481</td>\n",
              "      <td>29.750780</td>\n",
              "      <td>18.0</td>\n",
              "      <td>75.0</td>\n",
              "      <td>100.0</td>\n",
              "      <td>122.0</td>\n",
              "      <td>164.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2e3ff57f-58f3-4489-b757-cc283ed43ec4')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-2e3ff57f-58f3-4489-b757-cc283ed43ec4 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-2e3ff57f-58f3-4489-b757-cc283ed43ec4');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. Tokenizing, Filtering, Stopwords, Stemming"
      ],
      "metadata": {
        "id": "3pNTJhRJ5Cja"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! pip install Sastrawi"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MiP6cObT48O0",
        "outputId": "919a3c89-0070-4d97-efe0-f80c0ebd09cd"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting Sastrawi\n",
            "  Downloading Sastrawi-1.0.1-py2.py3-none-any.whl (209 kB)\n",
            "\u001b[K     |████████████████████████████████| 209 kB 28.5 MB/s \n",
            "\u001b[?25hInstalling collected packages: Sastrawi\n",
            "Successfully installed Sastrawi-1.0.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from textblob import TextBlob\n",
        "import re\n",
        "import nltk\n",
        "from nltk.corpus import stopwords\n",
        "from Sastrawi.Stemmer.StemmerFactory import StemmerFactory"
      ],
      "metadata": {
        "id": "RwKxz1q65NeU"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "nltk.download('punkt')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S-1qmPYr53gs",
        "outputId": "98c7a619-402f-4350-afa4-eb0cfe3e6181"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt.zip.\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "nltk.download('stopwords')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vU9KtkDd56Dc",
        "outputId": "efc81dc3-0a4e-4688-b79c-704e85d85915"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Unzipping corpora/stopwords.zip.\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Pipeline:"
      ],
      "metadata": {
        "id": "FvkN28aM59uC"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def text_preprocessing(tweet):\n",
        "\n",
        "    # TOKENIZING\n",
        "    # Generate word lists and remove punctuation\n",
        "    def form_sentence(tweet):\n",
        "        tweet_blob = TextBlob(tweet)\n",
        "        return ' '.join(tweet_blob.words.lower())\n",
        "    new_tweet = form_sentence(tweet)\n",
        "\n",
        "\n",
        "    # FILTERING\n",
        "    # Remove stopwords and words with unusual symbols\n",
        "    # Convert words to lowercase\n",
        "    def no_user_alpha(tweet):\n",
        "        tweet_list = [element for element in tweet.split() if element != '@']\n",
        "        clean_tokens = [t for t in tweet_list if re.match(r'[^\\W\\d]*$', t)]\n",
        "        clean_s = ' '.join(clean_tokens)\n",
        "        clean_mess = [word for word in clean_s.split() if word.lower() not in stopwords.words('indonesian')]\n",
        "        return clean_mess\n",
        "    no_punc_tweet = no_user_alpha(new_tweet)\n",
        "\n",
        "    # STEMMING\n",
        "    # Find basic indonesian words from tweet\n",
        "    def normalization(tweet_list):\n",
        "        normalized_tweet = []\n",
        "        factory = StemmerFactory()\n",
        "        stemmer = factory.create_stemmer()\n",
        "        for word in tweet_list:\n",
        "            normalized_text = stemmer.stem(word)\n",
        "            normalized_tweet.append(normalized_text)\n",
        "        return normalized_tweet\n",
        "    \n",
        "    \n",
        "    return normalization(no_punc_tweet)"
      ],
      "metadata": {
        "id": "8DWuE1XC58rU"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_test_over['tweet_list'] = data_test_over['tweet'].apply(text_preprocessing)"
      ],
      "metadata": {
        "id": "xzvS9I6i9FTM"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_test_over"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1877
        },
        "id": "Jg0Szg8j96Xw",
        "outputId": "3e6e3050-f989-484e-f91d-3a341fac2e1d"
      },
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      label                                              tweet  length  \\\n",
              "0    Non_HS  RT @spardaxyz: Fadli Zon Minta Mendagri Segera...     110   \n",
              "1    Non_HS  RT @baguscondromowo: Mereka terus melukai aksi...     108   \n",
              "2    Non_HS  Sylvi: bagaimana gurbernur melakukan kekerasan...     116   \n",
              "3    Non_HS  Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...     115   \n",
              "4    Non_HS  RT @lisdaulay28: Waspada KTP palsu.....kawal P...      79   \n",
              "..      ...                                                ...     ...   \n",
              "595      HS  Penista Agama menjadi Santri Kehormatan.Yang k...     140   \n",
              "595      HS  Penista Agama menjadi Santri Kehormatan.Yang k...     140   \n",
              "539      HS  Jangankan Banjir, Tuhan aja Dilawan Sama Ahok ...     112   \n",
              "514      HS  pertanyaan dari Bu Sylvi gak mutu amat. #Debat...      61   \n",
              "701      HS  Maksudnya terbukti KORUPSI dan PENISTAAN agama...     109   \n",
              "\n",
              "                                            tweet_list  \n",
              "0    [rt, spardaxyz, fadli, zon, mendagri, nonaktif...  \n",
              "1    [rt, baguscondromowo, luka, aksi, rangka, penj...  \n",
              "2    [sylvi, gurbernur, keras, perempuan, bukti, fo...  \n",
              "3    [ahmad, dhani, puas, debat, pilkada, jalan, be...  \n",
              "4     [rt, waspada, ktp, palsu, kawal, pilkada, https]  \n",
              "..                                                 ...  \n",
              "595  [nista, agama, santri, kasih, ahok, otak, pulk...  \n",
              "595  [nista, agama, santri, kasih, ahok, otak, pulk...  \n",
              "539  [banjir, tuhan, aja, lawan, ahok, jakartabanji...  \n",
              "514       [bu, sylvi, gak, mutu, debatfinalpilkadajkt]  \n",
              "701  [maksud, bukti, korupsi, nista, agama, nya, ya...  \n",
              "\n",
              "[906 rows x 4 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ebd44c7e-18ed-443f-b3c8-4c74d1ae9ebe\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>label</th>\n",
              "      <th>tweet</th>\n",
              "      <th>length</th>\n",
              "      <th>tweet_list</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @spardaxyz: Fadli Zon Minta Mendagri Segera...</td>\n",
              "      <td>110</td>\n",
              "      <td>[rt, spardaxyz, fadli, zon, mendagri, nonaktif...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @baguscondromowo: Mereka terus melukai aksi...</td>\n",
              "      <td>108</td>\n",
              "      <td>[rt, baguscondromowo, luka, aksi, rangka, penj...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Sylvi: bagaimana gurbernur melakukan kekerasan...</td>\n",
              "      <td>116</td>\n",
              "      <td>[sylvi, gurbernur, keras, perempuan, bukti, fo...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>Ahmad Dhani Tak Puas Debat Pilkada, Masalah Ja...</td>\n",
              "      <td>115</td>\n",
              "      <td>[ahmad, dhani, puas, debat, pilkada, jalan, be...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Non_HS</td>\n",
              "      <td>RT @lisdaulay28: Waspada KTP palsu.....kawal P...</td>\n",
              "      <td>79</td>\n",
              "      <td>[rt, waspada, ktp, palsu, kawal, pilkada, https]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>595</th>\n",
              "      <td>HS</td>\n",
              "      <td>Penista Agama menjadi Santri Kehormatan.Yang k...</td>\n",
              "      <td>140</td>\n",
              "      <td>[nista, agama, santri, kasih, ahok, otak, pulk...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>595</th>\n",
              "      <td>HS</td>\n",
              "      <td>Penista Agama menjadi Santri Kehormatan.Yang k...</td>\n",
              "      <td>140</td>\n",
              "      <td>[nista, agama, santri, kasih, ahok, otak, pulk...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>539</th>\n",
              "      <td>HS</td>\n",
              "      <td>Jangankan Banjir, Tuhan aja Dilawan Sama Ahok ...</td>\n",
              "      <td>112</td>\n",
              "      <td>[banjir, tuhan, aja, lawan, ahok, jakartabanji...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>514</th>\n",
              "      <td>HS</td>\n",
              "      <td>pertanyaan dari Bu Sylvi gak mutu amat. #Debat...</td>\n",
              "      <td>61</td>\n",
              "      <td>[bu, sylvi, gak, mutu, debatfinalpilkadajkt]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>701</th>\n",
              "      <td>HS</td>\n",
              "      <td>Maksudnya terbukti KORUPSI dan PENISTAAN agama...</td>\n",
              "      <td>109</td>\n",
              "      <td>[maksud, bukti, korupsi, nista, agama, nya, ya...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>906 rows × 4 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ebd44c7e-18ed-443f-b3c8-4c74d1ae9ebe')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-ebd44c7e-18ed-443f-b3c8-4c74d1ae9ebe button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-ebd44c7e-18ed-443f-b3c8-4c74d1ae9ebe');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Split Data (Training and Test)"
      ],
      "metadata": {
        "id": "j8EsGhzy-AO9"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "X = data_test_over['tweet']\n",
        "y = data_test_over['label']"
      ],
      "metadata": {
        "id": "pX1LgXtm9T1A"
      },
      "execution_count": 40,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)"
      ],
      "metadata": {
        "id": "UDaUCjD-9T3F"
      },
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Classification"
      ],
      "metadata": {
        "id": "a-iTZlTc_N_J"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.naive_bayes import MultinomialNB\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "\n",
        "from sklearn.pipeline import Pipeline\n",
        "from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer"
      ],
      "metadata": {
        "id": "ksDjJyLq_RBw"
      },
      "execution_count": 42,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 1. Random Forest"
      ],
      "metadata": {
        "id": "bfKyHBUu_Qg1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "pipeline_rnf = Pipeline([\n",
        "    ('bow', CountVectorizer(analyzer = text_preprocessing)),\n",
        "    ('tfidf', TfidfTransformer()), #weighted by TF-IDF score\n",
        "    ('classifier', RandomForestClassifier(n_estimators = 100)),\n",
        "])\n",
        "\n",
        "pipeline_rnf.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "z0MpnhKh9T5t",
        "outputId": "9a1ba958-a790-4e1b-e406-9c82fe1c652e"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Pipeline(steps=[('bow',\n",
              "                 CountVectorizer(analyzer=<function text_preprocessing at 0x7f5db6ebc680>)),\n",
              "                ('tfidf', TfidfTransformer()),\n",
              "                ('classifier', RandomForestClassifier())])"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. Multinomial Naive Bayes"
      ],
      "metadata": {
        "id": "D-s9F22rEXvh"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "pipeline_mnb = Pipeline([\n",
        "    ('bow', CountVectorizer(analyzer = text_preprocessing)),\n",
        "    ('tfidf', TfidfTransformer()), #weighted by TF-IDF score\n",
        "    ('classifier', MultinomialNB()),\n",
        "])\n",
        "pipeline_mnb.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J6NuI3gY9T7f",
        "outputId": "fcc3eb36-186c-4a0f-d1d8-3349ff74482a"
      },
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Pipeline(steps=[('bow',\n",
              "                 CountVectorizer(analyzer=<function text_preprocessing at 0x7f5db6ebc680>)),\n",
              "                ('tfidf', TfidfTransformer()),\n",
              "                ('classifier', MultinomialNB())])"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 3. KNN"
      ],
      "metadata": {
        "id": "cEO76tTlEarq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "pipeline_knn = Pipeline([\n",
        "    ('bow', CountVectorizer(analyzer = text_preprocessing)),\n",
        "    ('tfidf', TfidfTransformer()), #weighted by TF-IDF score\n",
        "    ('classifier', KNeighborsClassifier(n_neighbors=2)),\n",
        "])\n",
        "pipeline_knn.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LlYUd9OhD_0o",
        "outputId": "531aa7b5-1ba6-4211-d3aa-eee2729c028d"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Pipeline(steps=[('bow',\n",
              "                 CountVectorizer(analyzer=<function text_preprocessing at 0x7f5db6ebc680>)),\n",
              "                ('tfidf', TfidfTransformer()),\n",
              "                ('classifier', KNeighborsClassifier(n_neighbors=2))])"
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Evaluation Model"
      ],
      "metadata": {
        "id": "ZBzKJu1KFuAI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import metrics"
      ],
      "metadata": {
        "id": "61sIoXG8D_3n"
      },
      "execution_count": 45,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 1. The results of Random Forest Model"
      ],
      "metadata": {
        "id": "Gq3leTedGTWy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "predictions_rnf = pipeline_rnf.predict(X_test)\n",
        "\n",
        "print(\"==== Random Forest ====\")\n",
        "print(metrics.classification_report(predictions_rnf, y_test))\n",
        "print('\\n')\n",
        "print(metrics.confusion_matrix(predictions_rnf, y_test))\n",
        "print(metrics.accuracy_score(predictions_rnf, y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6F9bXvsw9T-a",
        "outputId": "95e35b3c-4742-428e-95c7-6ddc46e970b0"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "==== Random Forest ====\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "          HS       0.97      0.90      0.93        94\n",
            "      Non_HS       0.90      0.97      0.93        88\n",
            "\n",
            "    accuracy                           0.93       182\n",
            "   macro avg       0.94      0.94      0.93       182\n",
            "weighted avg       0.94      0.93      0.93       182\n",
            "\n",
            "\n",
            "\n",
            "[[85  9]\n",
            " [ 3 85]]\n",
            "0.9340659340659341\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. The results of Multinomial Naive Bayes Model\n"
      ],
      "metadata": {
        "id": "u9sigmtpGbIG"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "predictions_mnb = pipeline_mnb.predict(X_test)\n",
        "\n",
        "print(\"==== Multinomial Naive Bayes ====\")\n",
        "print(metrics.classification_report(predictions_mnb, y_test))\n",
        "print('\\n')\n",
        "print(metrics.confusion_matrix(predictions_mnb, y_test))\n",
        "print(metrics.accuracy_score(predictions_mnb, y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "h861CGgxGe4r",
        "outputId": "ad748b59-5afb-4db7-a9c7-b7a9cb89d392"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "==== Multinomial Naive Bayes ====\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "          HS       0.92      0.80      0.86       101\n",
            "      Non_HS       0.79      0.91      0.85        81\n",
            "\n",
            "    accuracy                           0.85       182\n",
            "   macro avg       0.85      0.86      0.85       182\n",
            "weighted avg       0.86      0.85      0.85       182\n",
            "\n",
            "\n",
            "\n",
            "[[81 20]\n",
            " [ 7 74]]\n",
            "0.8516483516483516\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 3. The results of KNN Model"
      ],
      "metadata": {
        "id": "-V7Isqh0GfXy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "predictions_knn = pipeline_knn.predict(X_test)\n",
        "\n",
        "print(\"==== KNN ====\")\n",
        "print(metrics.classification_report(predictions_knn, y_test))\n",
        "print('\\n')\n",
        "print(metrics.confusion_matrix(predictions_knn, y_test))\n",
        "print(metrics.accuracy_score(predictions_knn, y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nqmOHS6OGh_3",
        "outputId": "b9f7f0ad-7cc0-4aca-fe2d-74d64c9fcfbd"
      },
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "==== KNN ====\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "          HS       0.93      0.75      0.83       110\n",
            "      Non_HS       0.70      0.92      0.80        72\n",
            "\n",
            "    accuracy                           0.81       182\n",
            "   macro avg       0.82      0.83      0.81       182\n",
            "weighted avg       0.84      0.81      0.82       182\n",
            "\n",
            "\n",
            "\n",
            "[[82 28]\n",
            " [ 6 66]]\n",
            "0.8131868131868132\n"
          ]
        }
      ]
    }
  ]
}