Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task
Users of social media may use words and phrases literally to convey their views or opinion clearly. However, some people choose to utilise idioms or proverbs that are implicit and indirect in order to make a stronger impression on the audience or perhaps to catch their attention by utilising a funny...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2022
|
Online Access: | http://scholars.utp.edu.my/id/eprint/33886/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142809399&doi=10.1109%2fACCESS.2022.3222233&partnerID=40&md5=2f46a438255cfc5232a434f1863fb0b5 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:scholars.utp.edu.my:33886 |
---|---|
record_format |
eprints |
spelling |
oai:scholars.utp.edu.my:338862022-12-20T03:44:57Z http://scholars.utp.edu.my/id/eprint/33886/ Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task Tahayna, B. Ayyasamy, R.K. Akbar, R. Users of social media may use words and phrases literally to convey their views or opinion clearly. However, some people choose to utilise idioms or proverbs that are implicit and indirect in order to make a stronger impression on the audience or perhaps to catch their attention by utilising a funny, sarcastic, or metaphorical phrases. Idioms and proverbs are examples of figurative expressions with a thematically coherent totality that cannot be understood literally. In a previous work, the extension of IBM’s Sentiment Lexicon of Idiomatic Expressions was proposed to include around 9,000 idioms; both lexicons are manually annotated by crowdsourcing service. Therefore, in this research, we provide knowledge-based expansion approach to avoid human annotation of idioms. For sentiment classification, the proposed method has the advantage that it does not require any fine-tuning for the BERT model. Experimental comparisons show that the automated idiom enrichment and annotation are very beneficial for the performance of the sentiment classifier. The expanded annotated lexicon will be made available to the general public. Author Institute of Electrical and Electronics Engineers Inc. 2022 Article NonPeerReviewed Tahayna, B. and Ayyasamy, R.K. and Akbar, R. (2022) Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task. IEEE Access. p. 1. ISSN 21693536 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142809399&doi=10.1109%2fACCESS.2022.3222233&partnerID=40&md5=2f46a438255cfc5232a434f1863fb0b5 10.1109/ACCESS.2022.3222233 10.1109/ACCESS.2022.3222233 10.1109/ACCESS.2022.3222233 |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
description |
Users of social media may use words and phrases literally to convey their views or opinion clearly. However, some people choose to utilise idioms or proverbs that are implicit and indirect in order to make a stronger impression on the audience or perhaps to catch their attention by utilising a funny, sarcastic, or metaphorical phrases. Idioms and proverbs are examples of figurative expressions with a thematically coherent totality that cannot be understood literally. In a previous work, the extension of IBM’s Sentiment Lexicon of Idiomatic Expressions was proposed to include around 9,000 idioms; both lexicons are manually annotated by crowdsourcing service. Therefore, in this research, we provide knowledge-based expansion approach to avoid human annotation of idioms. For sentiment classification, the proposed method has the advantage that it does not require any fine-tuning for the BERT model. Experimental comparisons show that the automated idiom enrichment and annotation are very beneficial for the performance of the sentiment classifier. The expanded annotated lexicon will be made available to the general public. Author |
format |
Article |
author |
Tahayna, B. Ayyasamy, R.K. Akbar, R. |
spellingShingle |
Tahayna, B. Ayyasamy, R.K. Akbar, R. Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
author_facet |
Tahayna, B. Ayyasamy, R.K. Akbar, R. |
author_sort |
Tahayna, B. |
title |
Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
title_short |
Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
title_full |
Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
title_fullStr |
Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
title_full_unstemmed |
Automatic Sentiment Annotation of Idiomatic Expressions for Sentiment Analysis Task |
title_sort |
automatic sentiment annotation of idiomatic expressions for sentiment analysis task |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2022 |
url |
http://scholars.utp.edu.my/id/eprint/33886/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142809399&doi=10.1109%2fACCESS.2022.3222233&partnerID=40&md5=2f46a438255cfc5232a434f1863fb0b5 |
_version_ |
1753790749846011904 |
score |
13.18916 |