Emotion Analysis of Industry Research Report Based on the Hybrid Method of BERT and BiLSTM

Qi Luo and Mu Zhang ()
Additional contact information
Qi Luo: Guizhou University of Finance and Economics, School of Big Data Application and Economics
Mu Zhang: Guizhou University of Finance and Economics, School of Big Data Application and Economics

A chapter in Proceedings of the 10th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention (RAC 2022), 2023, pp 170-176 from Springer

Abstract: ABSTRACT In this era of information explosion, industry research papers contain a large number of information about the current business situation and profit and loss of enterprises, which reflects the credit risk of enterprises from the side, further affecting the objective evaluation of financial institutions such as banks. In order to improve the accuracy of the emotional analysis of industry research papers, this paper adopts the emotional analysis method based on the combination of BERT and BiLSTM, and selects 100 industry research papers from 38 industries of Dongfang Fortune Network in 2021 as samples for emotional analysis. To better demonstrate the performance of this model, this paper uses the SnowNLP model to compare with it. The results show that the accuracy, recall and F1 values based on the mixed model of BERT and BiLSTM are 85.42%, 82% and 83.68% respectively. The accuracy, recall and F1 value of SnowNLP model are 75%, 78% and 76.47% respectively. It can be concluded that the performance of the method proposed in this paper is good, and it has certain validity for the sentiment analysis of industry research papers, and has certain value in helping to predict the future development trend of the industry.

Keywords: BERT; BiLSTM; Industry Research Report; Affective Analysis (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-194-4_24

Ordering information: This item can be ordered from
http://www.springer.com/9789464631944

DOI: 10.2991/978-94-6463-194-4_24

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().