Publication: Transformer-based personality recognition from textual data
No Thumbnail Available
Date
2023-05
Journal Title
Journal ISSN
Volume Title
Publisher
Don Mariano Marcos Memorial State University - South La Union Campus
Abstract
Automatic personality trait recognition has become an area of growing interest
across the fields ofpsychology, neuropsychology, and computer science. With the success
of deep learning methods in various domains, researchers have increasingly employed
deep neural networks to learn high-level feature representations for automatic personality
trait recognition. In this study, a transformer-based personality recognition model is
proposed. Specifically, the authors utilized James Pennebaker and Laura King's streamof-consciousness essay and employed various text processing techniques. The researchers
trained various BERT-type models and found that the Distilbert-Base-Uncased
transformer using R-Adam optimizer achieved the highest F-score of O. 76, outperforming
other BERT-type models. Moreover, all proposed BERT-type models exhibited superior
performance compared to existing works that have used the same corpus in personality
trait recognition. The study demonstrates the effectiveness of transformer-based models
Description
Full text.
Keywords
Citation
San Juan, B. J. D., Agbuya, J. L., Ilano, A. J. D., & Lapore, R. C. M. (2023) Transformer-based personality recognition from textual data [Unpublished Undergraduate thesis]. Don Mariano Marcos Memorial State University - South La Union Campus, Agoo, La Union.