Character Personality Prediction Based on Deep Learning Algorithm MBTI

Yuanshen Su

2023

Abstract

The Myers-Briggs Type Indicator (MBTI) is a popular and extensively utilized tool for determining personality type. With the help of the Internet, the MBTI personality test, packaged by mass media, has become popular again in recent years. The MBTI personality test is helpful for people to seek their own identity and explore their strengths and weaknesses. This article will explore the collection of users’ online speech to predict user MBTI personality, so as to improve the platform’s help to users and improve service quality. The research topic of this paper is character prediction based on the deep learning algorithm MBTI. In this paper, six models are established using deep learning algorithms. Examples include the CatBoost Classifier and the XGBoost Classifier model. Use test set data to make predictions and find the accuracy of individual model prediction results. Among them, the prediction completed by the CatBoost Classifier model is the most accurate among the six models, with an accuracy of 0.668588. However, to make the prediction results more applicable, the predictive model is more confident. Research requires more data for model training to have better performance in real-world use. This research can help online platforms provide different help to users with different personality traits. For example, recommend jobs that suit people’s personality traits, or match and expand users’ circle of friends.

Paper Citation

in Harvard Style

Su Y. (2023). Character Personality Prediction Based on Deep Learning Algorithm MBTI. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 374-379. DOI: 10.5220/0012815900003885

in Bibtex Style

@conference{daml23,
author={Yuanshen Su},
title={Character Personality Prediction Based on Deep Learning Algorithm MBTI},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={374-379},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012815900003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Character Personality Prediction Based on Deep Learning Algorithm MBTI
SN - 978-989-758-705-4
AU - Su Y.
PY - 2023
SP - 374
EP - 379
DO - 10.5220/0012815900003885
PB - SciTePress