Bibliographic Details
| Title: |
Enhancing MBTI personality prediction: Integrating hybrid machine learning models with SMOTE for balanced data in predictive analytics. |
| Authors: |
Vikram, Vikram1 (AUTHOR) phdcs10002.21@bitmesra.ac.in, Gupta, Pankaj1 (AUTHOR) pgupta@bitmesra.ac.in |
| Source: |
AIP Conference Proceedings. 2025, Vol. 3253 Issue 1, p1-11. 11p. |
| Subject Terms: |
*MACHINE learning, *MYERS-Briggs Type Indicator, *PSYCHOLOGICAL typologies, *DATA analytics, *PERSONALITY |
| Abstract: |
In this study, we present a novel approach to improve Myers-Briggs Type Indicator (MBTI) personality prediction using machine learning techniques and Synthetic Minority Over-sampling Technique (SMOTE) for addressing class imbalance. Leveraging statement sentences as input data, our methodology integrates multiple Machine learning models, including Gradient Boosting, AdaBoost, XGBoost, and CatBoost classifiers, into a hybrid ensemble. We then employ SMOTE to balance the dataset, ensuring equal representation of all personality types. Furthermore, we train a neural network on the predictions from the ensemble models to capture complex patterns in the data. The combined predictions from the ensemble models and the neural network are evaluated using metrics such as accuracy score and classification report. Our results demonstrate the effectiveness of the proposed approach in enhancing MBTI personality prediction accuracy while addressing class imbalance, thereby advancing the field of predictive analytics in understanding human behavior and personality traits. [ABSTRACT FROM AUTHOR] |
|
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Academic Search Complete |
