Personality Traits Prediction from Text via Machine Learning

Social media platforms have been expanding their user bases. For example, LinkedIn counts 917 million monthly visitors, while Twitter has 3.62 billion monthly visitors. YouTube has 22.77 billion monthly visitors, and Instagram has 2.86 billion monthly visitors. Reports confirm data size increase of the social media networks above by 20–30% every day. With the spread of COVID-19, the same platforms have been broadly used by the worldwide collectiveness to socialize and stay amongst people. Analyzing text from Social Networking sites helps recognize individuals' personality traits automatically. A person's personality refers to their unique characteristics that shape their habits, behaviour, attitude, and cognitive tendencies. In this work, several machine learning techniques are surveyed to estimate personality traits from input text using the Myers-Briggs Type Indicator (MBTI) model. Experiments are run over a freely accessible dataset from Kaggle. In addition, techniques such as tokenization, word stemming, stop word elimination, and feature selection, utilizing TF-IDF, are used to analyze personality traits further.