Aspect-based sentiment analysis as fine-grained opinion mining

We show how the general fine-grained opinion mining concepts of opinion target and opinion expression are related to aspect-based sentiment analysis (ABSA) and discuss their benefits for resource creation over popular ABSA annotation schemes. Specifically, we first discuss why opinions modeled solel...

Full description

Bibliographic Details
Main Authors: Diaz, Gerardo Ocampo, Zhang, Xuanming, Ng, Vincent
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/64081/
_version_ 1848800087456612352
author Diaz, Gerardo Ocampo
Zhang, Xuanming
Ng, Vincent
author_facet Diaz, Gerardo Ocampo
Zhang, Xuanming
Ng, Vincent
author_sort Diaz, Gerardo Ocampo
building Nottingham Research Data Repository
collection Online Access
description We show how the general fine-grained opinion mining concepts of opinion target and opinion expression are related to aspect-based sentiment analysis (ABSA) and discuss their benefits for resource creation over popular ABSA annotation schemes. Specifically, we first discuss why opinions modeled solely in terms of (entity, aspect) pairs inadequately captures the meaning of the sentiment originally expressed by authors and how opinion expressions and opinion targets can be used to avoid the loss of information. We then design a meaning-preserving annotation scheme and apply it to two popular ABSA datasets, the 2016 SemEval ABSA Restaurant and Laptop datasets. Finally, we discuss the importance of opinion expressions and opinion targets for next-generation ABSA systems. We make our datasets publicly available for download.
first_indexed 2025-11-14T20:45:59Z
format Conference or Workshop Item
id nottingham-64081
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:45:59Z
publishDate 2020
recordtype eprints
repository_type Digital Repository
spelling nottingham-640812020-12-21T06:17:44Z https://eprints.nottingham.ac.uk/64081/ Aspect-based sentiment analysis as fine-grained opinion mining Diaz, Gerardo Ocampo Zhang, Xuanming Ng, Vincent We show how the general fine-grained opinion mining concepts of opinion target and opinion expression are related to aspect-based sentiment analysis (ABSA) and discuss their benefits for resource creation over popular ABSA annotation schemes. Specifically, we first discuss why opinions modeled solely in terms of (entity, aspect) pairs inadequately captures the meaning of the sentiment originally expressed by authors and how opinion expressions and opinion targets can be used to avoid the loss of information. We then design a meaning-preserving annotation scheme and apply it to two popular ABSA datasets, the 2016 SemEval ABSA Restaurant and Laptop datasets. Finally, we discuss the importance of opinion expressions and opinion targets for next-generation ABSA systems. We make our datasets publicly available for download. 2020-05-16 Conference or Workshop Item PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/64081/1/Aspect-based%20sentiment%20analysis%20as%20fine-grained%20opinion%20mining.pdf Diaz, Gerardo Ocampo, Zhang, Xuanming and Ng, Vincent (2020) Aspect-based sentiment analysis as fine-grained opinion mining. In: 12th Language Resources and Evaluation Conference, May 11-16, 2020, Marseille, France. opinion mining; sentiment analysis; text mining
spellingShingle opinion mining; sentiment analysis; text mining
Diaz, Gerardo Ocampo
Zhang, Xuanming
Ng, Vincent
Aspect-based sentiment analysis as fine-grained opinion mining
title Aspect-based sentiment analysis as fine-grained opinion mining
title_full Aspect-based sentiment analysis as fine-grained opinion mining
title_fullStr Aspect-based sentiment analysis as fine-grained opinion mining
title_full_unstemmed Aspect-based sentiment analysis as fine-grained opinion mining
title_short Aspect-based sentiment analysis as fine-grained opinion mining
title_sort aspect-based sentiment analysis as fine-grained opinion mining
topic opinion mining; sentiment analysis; text mining
url https://eprints.nottingham.ac.uk/64081/