A combination of lexicon-based and classified-based methods for sentiment classification based on Bert

Research output: Contribution to journalArticlepeer-review

11 Downloads (Pure)

Abstract

Abstract: Sentiment classification is a crucial problem in natural language processing and is essential to understand user opinions. There are two main approaches to solve this problem, one is the classified-based method, the other is the lexicon-based method; however, both methods perform not well on the long-sequence methods, and each method has its advantages and disadvantages. This paper introduced a new method called Lexiconed BERT, which cream off the best and filter out the impurities from the above two methods. The evaluation shows that our model achieves excellent results in the long sequence sentence and reduce resource consumption significantly.
Original languageEnglish
Article number032113
Number of pages7
JournalJournal of Physics: Conference Series
Volume1802
Issue number3
Early online date15 Nov 2020
DOIs
Publication statusPublished - 9 Mar 2021
EventThe 7th International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation - Busan, Korea, Democratic People's Republic of
Duration: 14 Nov 202015 Nov 2020
http://www.iccdmms.org/

Keywords

  • sentiment analysis
  • BERT
  • lexicon-based method

Fingerprint

Dive into the research topics of 'A combination of lexicon-based and classified-based methods for sentiment classification based on Bert'. Together they form a unique fingerprint.

Cite this