Personality Prediction based on Myers Briggs type Indicator Using Machine Learning

Abstract

In this study, we leverage a combination of machine learning algorithms, including classification and regression models, along with natural language processing techniques, such as NLP and spacy, to predict user personality types from their social media posts. We focus on utilizing the Myers-Briggs Type Indicator (MBTI) to identify a user's unique personality among sixteen possible types [1]. This research aims to establish a correlation between individuals' social media content and their personality traits. Our approach involves extensive preprocessing of textual data, employing techniques like text tokenization, regular expressions, lemmatization, sentiment analysis, and part-of-speech tagging, followed by dimensionality reduction [2]. We evaluate several machine learning models, including logistic regression, SVM, Naive Bayes, lasso regression, and random forest classifiers, with logistic regression delivering the most accurate results. We deploy this trained model on a web page connected to a Flask app, allowing users to input a brief description of themselves and receive their predicted personality type. This research explores the intersection of text analysis and personality prediction, shedding light on the hidden dimensions of human personality revealed through digital traces in the age of social media [4].