MBTI Based Personality Prediction of a User Based on Their Writing on Social Media
Neha Gupta1, Anirudh Madhavan2, Divya Duvvuri3, R.Angeline4

1Neha Gupta*, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
2Anirudh Madhavan, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
3Divya Duvvuri, Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India.
4R.Angeline,  Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India. 
Manuscript received on September 14, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 3372-3376 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1523109119/2019©BEIESP | DOI: 10.35940/ijeat.A1523.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The undeniable power that various e-commerce and streaming websites exert on their users’ in terms of what they buy and what they watch is unquestionable, so the creation of better targeted advertisements and recommender systems is the need of the hour. Prediction of a person’s personality can be the key for the achievement of these goals. A novel way to understand the various facets of a person’s personality is by analyzing their MBTI (Myers–Briggs Type Indicator). This paper aims at classifying a user into any one of the sixteen personality types, defined by MBTI, through the use of natural language processing (NLP) and support vector machine (SVM) which was implemented on the MBTI dataset. Since the original dataset is unevenly distributed, SVM has been applied to the original dataset and an under sampled version of the MBTI dataset. The highest accuracy rate of 78.52% for the traits (thinking/feeling) was achieved in the original dataset whereas for the under sampled dataset it was 60.2% for the traits (judging/perceiving).
Keywords: MBTI, NLP, Personality Prediction, SVM.