Papers by Kamyar Darvishi
Pars-ABSA: a Manually Annotated Aspect-based Sentiment Analysis Benchmark on Farsi Product Reviews (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing systems for sentiment analysis are focused on document and sentence levels, but there are no public datasets on aspect-based sentiment analysis for Farsi. |
| Approach: | They propose to use a manually annotated Farsi dataset to analyze the opinion polarity of reviews . they also use transfer learning to analyze aspects of the review to improve their results . |
| Outcome: | The proposed method performs better than other aspects of the existing system. |