A research attempt to predict and model personalities through users' social media details

Users of products and services, as human beings have a wide range of personalities. This is being experienced right from the initial days of e-commerce and m-commerce in India. In this research an attempt has been made to predict personalities using MBTI (Myers Briggs Type Indicator) based approach making use of natural language based processing, machine learning and transformer based modelling. As each human being is unique and exhibits different personality trait, therefore it is impractical to offer a generalized treatment for all users. But it is possible to categorize individuals, in terms of their defining characteristics based on MBTI based approach, which groups personalities/users into 16 groups and thus helps in predicting personalities. In this study authors made an attempt to extract social media based information of users through their accounts to characterize users into one of the 16 MBTI personality types. For this prediction and modelling, authors made use of pre-processed data from Kaggle, which was then fed into the transformer for modelling/processing. Based on the information it gets, like comments, post captions, reviews, etc., the transformer is fine-tuned to predict the user's personality. The required qualities of the model were taken into account while coding the transformer's parameters. Additionally, an attempt is also made to compare the outcomes of two trained transformer models. Authors report that the prediction accuracy of their modelling as 64%, outperforming all other models used. The testing data had a 76% precision.