Fine-Tuning IndoBERT Model for Big Five Personality Prediction from Indonesian Social Media

Pradnyana, Gede Aditra; Anggraeni, Wiwik; Yuniarno, Eko Mulyanto; Purnomo, Mauridhi Hery

doi:10.1109/isitia59021.2023.10221074

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional preprocessing measures were undertaken by incorporating specific tokens, namely [CLS] at the commencement of the sentence, [SEP] at its conclusion, and [PAD] in instances of shorter sentences [16]. The subsequent phase entails the division of the data utilizing the hold-out technique.…”

Section: Research Implementationmentioning

confidence: 99%

Classification Performance Comparison of BERT and IndoBERT on SelfReport of COVID-19 Status on Social Media

Budiman,

Faisal,

Faridhah

et al. 2024

J. Comput. Sci. Inst.

View full text Add to dashboard Cite

Messages shared on social media platforms like X are automatically categorized into two groups: those who self-report COVID-19 status and those who do not. However, it is essential to note that these messages cannot be a reliable monitoring tool for tracking the spread of the COVID-19 pandemic. The classification of social media messages can be achieved through the application of classification algorithms. Many deep learning-based algorithms, such as Convolutional Neural Networks (CNN) or Long Short-Term Memory (LSTM), have been used for text classification. However, CNN has limitations in understanding global context, while LSTM focuses more on understanding word-by-word sequences. Apart from that, both require a lot of data to learn. Currently, an algorithm is being developed for text classification that can cover the shortcomings of the previous algorithm, namely Bidirectional Encoder Representations from Transformers (BERT). Currently, there are many variants of BERT development. The primary objective of this study was to compare the effectiveness of two classification models, namely BERT and IndoBERT, in identifying self-report messages of COVID-19 status. Both BERT and IndoBERT models were evaluated using raw and preprocessed text data from X. The study's findings revealed that the IndoBERT model exhibited superior performance, achieving an accuracy rate of 94%, whereas the BERT model achieved a performance rate of 82%.

show abstract

Section: Research Implementationmentioning

confidence: 99%

Classification Performance Comparison of BERT and IndoBERT on SelfReport of COVID-19 Status on Social Media

Budiman,

Faisal,

Faridhah

et al. 2024

J. Comput. Sci. Inst.

View full text Add to dashboard Cite

show abstract

PersoNet: A Novel Framework for Personality Classification-Based Apt Customer Service Agent Selection

Sandra,

Prabowo,

Gaol

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Personality classification has garnered significant interest in psychology, computational social science, and Machine Learning (ML) due to its wide-ranging applications. This paper presents PersoNet, an innovative framework developed to identify personality types using the Myers-Briggs Type Indicator (MBTI), aimed at enhancing customer service experiences by matching customers with suitable support agents. PersoNet employs a Bidirectional Long Short-Term Memory (BiLSTM) neural network architecture and has achieved an impressive classification accuracy of over 93.98%. Our extensive experiments with the MBTI dataset reveal that the BiLSTM architecture effectively captures both temporal dependencies and semantic subtleties in textual data, contributing to this high level of accuracy. Consequently, PersoNet can accurately select customer service agents who match customer personalities, achieving a Customer Satisfaction Rate (CSR) of over 97.82%-a notable improvement of 20.25% in CSR based on our experimental data. These results establish PersoNet as a cutting-edge tool in personality classification, surpassing existing methods in both accuracy and computational efficiency and markedly enhancing customer service quality.

show abstract

A Survey of Semantic Approaches in Personality Traits Profiling Analysis

Hartanto,

Utami,

Kusrini

et al. 2024

2024 International Conference on Smart Computing, IoT and Machine Learning (SIML)

View full text Add to dashboard Cite

Fine-Tuning IndoBERT Model for Big Five Personality Prediction from Indonesian Social Media

Cited by 3 publications

References 19 publications

Classification Performance Comparison of BERT and IndoBERT on SelfReport of COVID-19 Status on Social Media

Classification Performance Comparison of BERT and IndoBERT on SelfReport of COVID-19 Status on Social Media

PersoNet: A Novel Framework for Personality Classification-Based Apt Customer Service Agent Selection

A Survey of Semantic Approaches in Personality Traits Profiling Analysis

Contact Info

Product

Resources

About