MBTI personality classification using Apache Spark

Loading...
Thumbnail Image

Date

2021

Journal Title

Journal ISSN

Volume Title

Publisher

ResearchGate

Abstract

Personality determines how person make decisions, speak or react on different situations. In this paper explained shortly the specifics of Myers-Briggs Type Indicator personality classification, then details of preparation of the experiment to run on Apache Spark platform. In experiment three different classification algorithms (Logistic Regression, Naive Bayes, Support Vector Machine) are used to train and predict MBTI personality pairs on a Kaggle dataset consisting of 8675 users tweets. In the end explained the data preprocessing and algorithm training, testing, validation details and results. The models with different vector combinations have been compared, and results have been described.

Description

Keywords

MBTI, Apache Spark, Logistic Regression

Citation

Orynbekova K , Talasbek A , Omar A / MBTI personality classification using Apache Spark / ResearchGate / 2021