A Study on Employment Problems and Sentiment Analysis of College Students Based on Bert-BiLSTM

DOI

10.2991/978-94-6463-540-9_71How to use a DOI?

Keywords

Sentiment analysis; BiLSTM; BERT; employment attitude text; Attention mechanism

Abstract

In recent years, Chinese college students have generally faced social problems such as fierce competition for employment and rising youth unemployment. Sentiment analysis of college students’ employment attitudes helps them recognize the situation, accurately position themselves, and rationally arrange their college life. Therefore, this study suggests a BERT-BiLSTM-based sentiment classification model that can categorize comments’ emotions into three groups: positive, neutral, and negative, and uses big data mining to explore factors contributing to college student employment issues. The scheme employs the bidirectional encoder representations from transformers (BERT) pertaining model for sentence segmentation and word vectorization, and then feeds the bidirectional long short-term memory (BiLSTM) model with the processing results in order to do thorough feature mining for sentiment polarity categorization and aspect separation. The evaluation metrics are accuracy rate and loss rate. Considering the outcomes of the experiment, Bert-BiLSTM technique achieves 0. 7522 in accuracy rate and 0. 5891 in loss rate. In contrast to applying the Bert model (0. 7269, 0. 6138) and the LSTM model (0. 6252, 0. 6836) alone, it exhibits a certain advantage in the final results. The study’s results can relatively accurately predict the emotional tendency of college students’ employment in contemporary society, thus providing emotional guidance and suggesting directions for related social issues such as college students’ mental health and employment choices.

Copyright

© 2024 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  - Zihan Chen
PY  - 2024
DA  - 2024/10/16
TI  - A Study on Employment Problems and Sentiment Analysis of College Students Based on Bert-BiLSTM
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 693
EP  - 703
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_71
DO  - 10.2991/978-94-6463-540-9_71
ID  - Chen2024
ER  -