Improving Document-level Sentiment Analysis with User and Product Context
Citation:
Chenyang Lyu, Jennifer Foster, Yvette Graham, Improving Document-level Sentiment Analysis with User and Product Context, Proceedings of the 28th International Conference on Computational Linguistics (COLING), 28th International Conference on Computational Linguistics (COLING), Virtual, Association for Computational Linguistics, 2020, 6724 - 6729Download Item:
Abstract:
Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text available at the time of sentiment prediction that may prove meaningful for guiding prediction. Firstly, we incorporate all available historical review text belonging to the author of the review in question. Secondly, we investigate the inclusion of historical reviews associated with the current product (written by other users). We achieve this by explicitly storing representations of reviews written by the same user and about the same product and force the model to memorize all reviews for one particular user and product. Additionally, we drop the hierarchical architecture used in previous work to enable words in the text to directly attend to each other. Experiment results on IMDB, Yelp 2013 and Yelp 2014 datasets show improvement to state-of-the-art of more than 2 percentage points in the best case.
Sponsor
Grant Number
SFI stipend
18/CRT/6183
Author's Homepage:
http://people.tcd.ie/ygrahamDescription:
PUBLISHEDVirtual
Author: Graham, Yvette
Sponsor:
SFI stipendOther Titles:
Proceedings of the 28th International Conference on Computational Linguistics (COLING)28th International Conference on Computational Linguistics (COLING)
Publisher:
Association for Computational LinguisticsType of material:
Conference PaperCollections
Availability:
Full text availableSubject (TCD):
Digital Engagement , Inclusive Society , ARTIFICIAL INTELLIGENCE , Natural Language Processing , sentiment analysisDOI:
http://dx.doi.org/10.18653/v1/2020.coling-main.590Metadata
Show full item recordLicences: