Loading...
Comparative Analysis Of Convolutional Neural Networks, Long Short-Term Memory Networks, and Bert For Text-Based Emotion Classification
Author(s)
Visutsak, Porawat
Tongbai, Tanajak
Ongrungruaeng, Duongduen
Phongwuttisak, Nuttiruj
Wiriya, Surapong
Ryu, Keun Ho
Date Issued
June 1, 2026
Type
Article
Abstract
This paper presents a detailed experimental study and comparative analysis of three popular deep learning architectures (CNN, LSTM, and BERT) for emotion classification in written messages. Using a publicly available dataset of six unique emotional states (sadness, joy, love, anger, fear, and surprise), an effective ablation study was conducted to determine optimal architectural configurations, including a sequence length of 66 tokens and an embedding size of 200. To validate the results of a comparative analysis of model performance, a bootstrap technique (30 trials) and the Wilcoxon Signed-Rank test were used to eliminate potential bias. As shown by experiments, the tuned BERT architecture (with a learning rate of 2e-5) produced the most accurate and reliable result of 93.50% in classifying emotional states from texts. Moreover, with an appropriate sequence length configuration, the LSTM network (89.92%) significantly outperformed the CNN (89.65%), confirming the need to account for long-range dependencies in emotion classification. Overall, the research results show the key importance of hyperparameter tuning and the ability to handle complex information for emotion identification.
Citation
Asean Journal of Scientific and Technological Reports, 29(6), 2026