Research on text data sentiment analysis algorithm integrating transfer learning and hierarchical attention network

Qiang Wu

International Journal of Networking and Virtual Organisations, 2023, vol. 28, issue 2/3/4, 301-317

Abstract: The rapid development of the internet has changed the way people express their opinions and emotions. How to use high-performance sentiment analysis algorithms for practical auxiliary product recommendation and public opinion analysis has become a research hotspot. This research proposes a text data sentiment analysis algorithm that integrates transfer learning and hierarchical attention network, and conducts sentiment analysis on single domain and cross domain text data and verifies the effectiveness of the algorithm. The results show that the TLHANN algorithm has an accuracy of 0.85 in IMDB2 data samples, which is higher than other algorithms. In the field of books and DVDs, the accuracy of this algorithm is 0.83, while the other algorithms are 0.826 and 0.828, respectively, which are lower than the FMCSC algorithm. This verifies the effectiveness of the cross domain text sentiment analysis FMCSC algorithm and further verifies its optimal performance.

Keywords: transfer learning; hierarchical attention; sentiment analysis; TLHANN algorithm; FMCSC algorithm. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=133862 (text/html)
Access to full text is restricted to subscribers.

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:ids:ijnvor:v:28:y:2023:i:2/3/4:p:301-317

Access Statistics for this article

More articles in International Journal of Networking and Virtual Organisations from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().