Personality Prediction Based on Twitter Data

The aim of this project is to predict the personality traits of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism based on Twitter usage data and to determine the best models to predict the personality.

This study applies the personality prediction of a Twitter user based on the words used in tweets posted by the user. The personality type is predicted based on the Big Five Personality Model and outputs are agreeableness, conscientiousness, openness, neuroticism, and extraversion as personality traits. To predict each personality trait, most successful machine learning methods are selected.

Social media has grabbed the attention of the current generation of people and became very much accessible on the internet. The activity performed by social media users provides a better platform for researchers to study and learn about online behaviors, preferences, and personality traits. We are using Twitter as a leading social media platform for the analysis since the number of users is intense. To analyze the person's nature, the user data can be extracted and perform further analysis based on the text, status profiles, or preferences provided to other users on Twitter. To understand the different forms of texts, the comment added by the user, tweet, social behavior, and the usage of language habits on Twitter is taken as the data for analysis. This research can be taken further by using Machine Learning algorithms to process the data and the user's actual prediction personality.

Algorithm:

• KNN
• Decision Tree
• Random Forest(RF)
• AdaBoost
• Stochastic gradient descent(SGD)
• Gradient boosting(GB)
• SVM