Chinese Financial Comments Sentiment Detection Based on the Bert-TCN Model Based on HowNet Disambiguation

DOI

10.2991/978-94-6463-304-7_18How to use a DOI?

Keywords

NLP; Bert; TCN; HowNet; WSD

Abstract

The introduction of investor sentiment index has set an important milestone in quantitative research within the financial industry. The index became a powerful tool for extracting insights from investors’ opinions about future financial markets. In order to solve the problem of ambiguity in Chinese financial news sentiment analysis, we design and implement a BERT model based on HowNet. This study not only provides a comparative analysis of the performance of multiple models such as LSTM, RNN, CNN and BERT on sentiment classification tasks, but also delves into the actual impact of ambiguity resolution on classification results. On top of this, it also conducts a subsequent empirical test of stock prices using sentiment scores. The experimental results verify the excellent performance of our model in sentiment classification, especially in dealing with ambiguity, which provides a strong impetus for sentiment analysis and stock prediction in the Chinese financial field. Overall, this research opens a completely new path for the application of sentiment analysis and prediction in the Chinese financial industry.

Copyright

© 2023 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  - Linhan Xia
PY  - 2023
DA  - 2023/12/04
TI  - Chinese Financial Comments Sentiment Detection Based on the Bert-TCN Model Based on HowNet Disambiguation
BT  - Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)
PB  - Atlantis Press
SP  - 153
EP  - 168
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-304-7_18
DO  - 10.2991/978-94-6463-304-7_18
ID  - Xia2023
ER  -