An Approach for Sentiment Analysis and Personality Prediction Using Myers Briggs Type Indicator

摘要

Due to the rapid development of "Web 5.0", in the last few years, researchers have started to pay attention to social media using Personality Prediction and Sentiment Analysis. However, due to the high costs and the privacy of these datasets, this paper presents a study on Sentiment Analysis and Personality Prediction through Social Media using Myers-Briggs Type Indicator (MBTI) personality assessment test to analyze textual data with the use of different classification algorithms. The data are collected from Kaggle with approximately 8600 rows of Twitter data. The system is tested using 25% of the dataset and the remaining 75% is for the training set. The results show an average accuracy rate of 78.2% with the use of different classification algorithms, and a 100% accuracy rate using the Random Forest (RF) and Decision Tree classifiers.