Depressive Post Classification using Transformer Models
Published in 2023 26th International Conference on Computer and Information Technology (ICCIT), 2023
In our rapidly evolving contemporary world, mental health is of paramount importance, alongside physical well-being. There has been a concerted effort to raise awareness about the critical significance of mental health. Following the pandemic, social media data are increasingly used to gain insights into the detection of mental health conditions, as more individuals turn to online platforms to express their emotions. Previous research has employed shallow machine learning models and deep learning models such as BERT to detect depression from social media data. It has been demonstrated that Transformer-based models provide a robust toolkit for accurately and sensitively analyzing social media posts to detect signs of depression. This research aims to evaluate the performance of various transformer models that have not been explored within this domain. Upon close comparison with previous studies, it has been observed that our approach outperforms prior research work
Recommended citation: I. Newaz, A. W. Quader and M. J. A. Patwary, “Depressive Post Classification using Transformer Models,” 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox’s Bazar, Bangladesh, 2023, pp. 1-6, doi: 10.1109/ICCIT60459.2023.10441302.
Recommended citation: I. Newaz, A. Quader, M. Patwary, "Depressive Post Classification using Transformer Models," in 2023 26th International Conference on Computer and Information Technology (ICCIT), 2023, pp. 1-6.
Download Paper