Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Ekapratiwi, Dian
Unknown Affiliation
Computer Science & IT Control & Systems Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Personality Classification of Myers Briggs Type Indicators (MBTI) Using BERT and Machine Learning Sihabuddin, Agus; Ekapratiwi, Dian
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 2 (2025): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.104126

Abstract

Personality classification using textual data from social media or online forums is a complex task due to the unstructured text and the multifaceted nature of personality. While the Myers-Briggs Type Indicator (MBTI) provides a comprehensive framework, adapting it to media data and handling diverse linguistic patterns requires effective algorithms. The psychological basis of MBTI is intricate, especially when using complex methods like deep learning, which can be challenging.      This study classifies personality types based on each individual's behavior on an online forum by observing the linguistic patterns of posted textual data using the SVM, Random Forest, BERT, and Word2Vec algorithms. The SVM and Random Forest algorithms are traditional machine learning algorithms known for their capabilities and effectiveness in text classification. Meanwhile, BERT and Word2Vec identify semantic relationships and contextual information from textual data. In addition, the IndoBERT model will be used for the BERT model because this study focuses on the classification of Indonesian language texts.Testing was carried out using textual data from posts on the PersonalityCafe forum. The test results showed that the combination of the SVM and IndoBERT models outperformed other models with an accuracy rate of 82% and an F1 score of 75%.
Co-Authors Agus Sihabuddin