Data consists of tweets scrapped using Twitter API. Objective is sentiment labelling using a lexicon approach, performing text pre-processing (such as language detection, tokenisation, normalisation, vectorisation), building pipelines for text classification models for sentiment analysis, followed by explainability of the final classifier

Recognizes the subject of websites

Develop Machine Learning models to predict sentiments on COVID-19 tweets.

Conducting sentiment analysis on custom dataset more than 90000 statements mapped to 11 different emotions. Comparing the accuracy between LinearSVC, RandomForestClassifier and LSTM based models. Implementing the results in a chatbot powered by Gemini API.

Harmonizing Hearts: A Music-Based Compatibility Analysis

Repo for the exam of the course 'Introduction to ML for NLP'

E-mail classification using LinearSVC algorithm

This Jupyter Notebook serves as a comprehensive guide to performing support vector machine (LinearSVC) classification and calculating accuracy scores for machine learning tasks. It provides step-by-step instructions and code examples for building, training, and evaluating a LinearSVC classifier

Using Collaborative Filtering predicting Movie Rating and K-nearest Neighbours & SVM algorithms for Number ClassificationNumber Classification

This project refactored code to build an SMS spam detection model using a linear SVC pipeline with TF-IDF vectorization. The model was integrated into a Gradio interface, enabling real-time user predictions of whether a text message is spam or not, demonstrating the practical application of language models in text classification tasks.