DC FieldValueLanguage
dc.contributor.authorŽunić, Anastaziaen_US
dc.contributor.authorCorcoran, Padraigen_US
dc.contributor.authorSpasić, Irenaen_US
dc.date.accessioned2022-12-09T13:09:44Z-
dc.date.available2022-12-09T13:09:44Z-
dc.date.issued2022-
dc.identifier.issn2504-4990-
dc.identifier.urihttp://researchrepository.mi.sanu.ac.rs/handle/123456789/4931-
dc.description.abstract(1) Background: Aspect-based sentiment analysis (SA) is a natural language processing task, the aim of which is to classify the sentiment associated with a specific aspect of a written text. The performance of SA methods applied to texts related to health and well-being lags behind that of other domains. (2) Methods: In this study, we present an approach to aspect-based SA of drug reviews. Specifically, we analysed signs and symptoms, which were extracted automatically using the Unified Medical Language System. This information was then passed onto the BERT language model, which was extended by two layers to fine-tune the model for aspect-based SA. The interpretability of the model was analysed using an axiomatic attribution method. We performed a correlation analysis between the attribution scores and syntactic dependencies. (3) Results: Our fine-tuned model achieved accuracy of approximately (Formula presented.) on a well-balanced test set. It outperformed our previous approach, which used syntactic information to guide the operation of a neural network and achieved an accuracy of approximately (Formula presented.). (4) Conclusions: We demonstrated that a BERT-based model of SA overcomes the negative bias associated with health-related aspects and closes the performance gap against the state-of-the-art in other domains.en_US
dc.publisherMDPIen_US
dc.relation.ispartofMachine Learning and Knowledge Extractionen_US
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectdeep learning | natural language processing | sentiment analysis | syntactic dependencies | transformersen_US
dc.titleThe Case of Aspect in Sentiment Analysis: Seeking Attention or Co-Dependency?en_US
dc.typeArticleen_US
dc.identifier.doi10.3390/make4020021-
dc.identifier.scopus2-s2.0-85141350096-
dc.contributor.affiliationComputer Scienceen_US
dc.contributor.affiliationMathematical Institute of the Serbian Academy of Sciences and Artsen_US
dc.relation.firstpage474-
dc.relation.lastpage487-
dc.relation.issue2-
dc.relation.volume4-
item.cerifentitytypePublications-
item.grantfulltextopen-
item.openairetypeArticle-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextWith Fulltext-
crisitem.author.orcid0000-0001-5222-1268-
Files in This Item:
File Description SizeFormat
AZunic.pdf804.74 kBAdobe PDFView/Open
Show simple item record

SCOPUSTM   
Citations

2
checked on Jun 20, 2024

Page view(s)

38
checked on May 9, 2024

Download(s)

28
checked on May 9, 2024

Google ScholarTM

Check

Altmetric

Altmetric


This item is licensed under a Creative Commons License Creative Commons