Personality Identification from Social Media Using Ensemble Bert and Roberta

Eggi Farkhan Tsani, Derwin Suhartono


Social media growth was fast because many people use it to express their feelings, shared information, and interact with others. With this growth of social media, many researchers are interested in using social media data to conduct research about personality identification. The identification result can be used as a parameter to screen candidate attitudes in the company recruitment process. Some approaches were used for research about personality; one of the most used is Big Five Personality. In this research, an ensemble model between BERT and RoBERTa was introduced for personality prediction from the Twitter and Youtube datasets. Data augmentation method also introduce for handling the imbalance class for each dataset. Pre-trained model BERT and RoBERTa was used as the feature extraction method and modeling process. To predict each trait in Big Five Personality, the voting ensemble from BERT and RoBERTa achieved an average f1 score 0,730 for Twitter dataset and 0,741 for Youtube dataset. Using the proposed model, we conclude that data augmentation can increase average performance compared to the model without data augmentation process.

Full Text:



Sprockets, "The Importance of Recruiting for Personality: Everything You Need to Know," personality.

R. Shilpa, V. Supriya, P. Sweta, V. R. Vinaya, and S. S. Uday, "Personality prediction using Machine Learning," Science and Engineering Journal, vol. 25, no.7, pp. 46-53, 2021.

R. Valanarasu, "Comparative analysis for personality prediction by digital footprints in social media," Journal of Information Technology and Digital World, vol. 3, no. 02, pp. 77-91, 2021.

Datareportal, "Digital 2021: Indonesia," indonesia.

N. A. Utami, W. Maharani, and I. Atastina, "Personality classification of Facebook users according to Big Five Personality using SVM (Support Vector Machine) method," Procedia Computer Science, vol. 179, pp. 177-184, 2021.

N. Abood, "Big five traits: A critical review," Gajah Mada International Journal of Business, vol. 21, no. 2, pp. 159-186, 2019.

S. Basaran, and O. H. Ejimogu, "A Neural Network Approach for Predicting Personality from Facebook Data," Sage Journals, vol. 11, no. 3, 2021.

Computer Vision Center and University of Barcelona, "ChaLearn Looking at People,"

T. Tandera, D. Suhartono, R. Wongso, and Y. L. Prasetio, "Personality Prediction System from Facebook Users," Procedia Computer Science, vol. 116, pp. 604-611, 2017.

M. M. Tadesse, H. Lin, B. Xu, and L. Yang, "Personality predictions based on user behavior on the Facebook social media platform," IEEE Access, vol. 6, pp. 61959-61969, 2018.

G. Y. Adi, M. H. Tandio, V. Ong, and D. Suhartono, "Optimization for Automatic Personality Recognition on Twitter in Bahasa Indonesia," Procedia Computer Science, vol. 135, pp. 473-480, 2018.

N. H. Jeremy, C. Prasetyo, and D. Suhartono, "Identifying Personality Traits for Indonesian User from Twitter Dataset," International Journal of Fuzzy Logic and Intelligent Systems, vol. 4, pp. 283-289, 2019.

H. Christian, D. Suhartono, A. Chowanda, and K. Z. Zamli, "Text based personality prediction from multiple social media data sources using pre‐trained language model and model averaging," Journal of Big Data, vol. 8, no. 68, 2021.

G. Farnadi, G. Sitaraman, S. Sushmita, F. Celli, M. Kosinski, D. Stillwell, S. Davalos, M. Moens, and M. D. Cock, "Computational personality recognition in social media," Springer Science and Business Media LLC, vol. 26, pp. 109-142, 2016.

F. O. Lopez-Pabon, and J. R. Orozco-Arroyave, "Automatic Personality Evaluation from Transliterations of Youtube Vlogs using Classical and State-of-the-Art Word Embeddings," Ingeneria e Investigacion, vol. 42, no. 2, 2022.

Machine Learning Mastery, "A Gentle Introduction to Ensemble Learning Algorithms," 2021.

H. Zheng, and C. Wu, "Predicting personality using facebook status based on semi-supervise learning," in Proceedings of the 2019 11th International Conference on Machine Learning and Computing, 2019, pp. 59-64.

A. Souri, S. Hosseinpor, and A. M. Rahmani, "Personality classification based on profiles of social network users and the five-factor model of personality," Human-centric Computing and Information Sciences, vol. 8, no. 24, 2018.

M. U. Maheswari, and J. G. R. Sathiaseelan, "Text Mining; Survey on Techniques and Applications," International Journal of Science and Research, vol. 6, no. 6, pp. 1660-1664, 2017.

Towards Data Science, "Paraphrase any question with T5 (Text-To-Text Transfer Transformer) - Pretrained model and training script provided," question-with-t5-text-to-text-transfer-transformer- pretrained-model-and-cbb9e35f1555.

P. Kaur, G. S. Kohli, and J. Bedi. "Classification of Health-Related Tweets Using Ensemble, Zero-Shot and Fine-Tuned Language Model," in Proceedings of the 29th International Conference on Computational Linguistic, 2022, pp. 138-142.

J. Liu, C. Xia, X. Li, H. Yan, and T. Liu, "A BERT- based Ensemble Model for Chinese News Topic Prediction," ACM Digital Library, pp. 18-23, 2020.

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, "Attention is all you need," in 31st Conference on Neural Information Processing Systems, 2017.

M. E. Peters, M. Neumann, L. Zettlemoyer, and W. T. Yih, "Dissecting contextual word embeddings: Architecture and representation," in Proceedings of the 2018 Conference of Empirical Method in Natural Language Processings, 2020, pp. 1499-1509.

A. Kulkarni, D. Chong, and F. A. Batarseh, " 8," Nexus of Artificial Intelligence, Software Development, and Knowledge Engineering, pp. 83- 106, 2020.

Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, "Albert: A lite bert for self-supervised learning of language representations," arXiv preprint arXiv, 2019.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.