Student Behavior Prediction and Emotion Management Based on Natural Language Processing

DOI

10.2991/978-2-38476-511-9_81How to use a DOI?

Keywords

Natural language processing; student behavior prediction; emotion management; ABLSTM-Transformer algorithm

Abstract

Students’ behavior prediction and emotion management play an important role in educational decision making. In this paper, a new algorithm called ABLSTM-Transformer is proposed. It integrates bidirectional long short-term memory network, attention mechanism and transformer architecture to deal with students’ text data. According to 7: 2: 1, 20,000 text data collected from educational platform were divided into training set, validation set and test set. The ABLSTM-Transformer algorithm uses precision, recall and F1 as evaluation indicators to compare LSTM and TextCNN algorithms. The results show that ABLSTM-Transformer algorithm achieves 92.3% accuracy, 91.5% recall rate and 91.9% F1 value; on emotion classification task, its precision is 93.1%, recall 92.6%, F1 92.8%. For behavior prediction tasks, three indicators were 85.2%, 84.1% and 84.6% respectively; for emotion classification tasks, 86.3%, 85.5%, 85.9%; TextCNN algorithm was 87.6%; 86.3%; 86.9%; 87.6%; 87.6%; 87.1%; 87.6%; 87.6%; Experimental results show that ABLSTM-Transformer has better performance in prediction of students’ behavior and emotion management.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiaoxia Hao
PY  - 2025
DA  - 2025/12/31
TI  - Student Behavior Prediction and Emotion Management Based on Natural Language Processing
BT  - Proceedings of the 7th International Conference on Literature, Art and Human Development (ICLAHD 2025)
PB  - Atlantis Press
SP  - 705
EP  - 712
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-511-9_81
DO  - 10.2991/978-2-38476-511-9_81
ID  - Hao2025
ER  -