Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews
Online reviews are an important source of opinion to measure products’ quality. Hence, automated opinion mining is used to extract important features (aspect) and related comments (sentiment). Extraction of correct aspect-sentiment pairs is critical for overall outcome of opinion mining; h...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-11-01
|
Series: | Informatics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9709/5/4/45 |
_version_ | 1811270861462700032 |
---|---|
author | Noor Rizvana Ahamed Kabeer Keng Hoon Gan Erum Haris |
author_facet | Noor Rizvana Ahamed Kabeer Keng Hoon Gan Erum Haris |
author_sort | Noor Rizvana Ahamed Kabeer |
collection | DOAJ |
description | Online reviews are an important source of opinion to measure products’ quality. Hence, automated opinion mining is used to extract important features (aspect) and related comments (sentiment). Extraction of correct aspect-sentiment pairs is critical for overall outcome of opinion mining; however, current works still have limitations in terms of identifying special compound noun and parent-child relationship aspects in the extraction process. To address these problems, an aspect-sentiment pair extraction using the rules and compound noun lexicon (ASPERC) model is proposed. The model consists of three main phases, such as compound noun lexicon generation, aspect-sentiment pair rule generation, and aspect-sentiment pair extraction. The combined approach of rules generated from training sentences and domain specific compound noun lexicon enable extraction of more aspects by firstly identifying special compound noun and parent-child aspects, which eventually contribute to more aspect-sentiment pair extraction. The experiment is conducted with the SemEval 2014 dataset to compare proposed and baseline models. Both ASPERC and its variant, ASPER, result higher in recall (28.58% and 22.55% each) compared to baseline and satisfactorily extract more aspect sentiment pairs. Lastly, the reasonable outcome of ASPER indicates applicability of rules to various domains. |
first_indexed | 2024-04-12T22:10:19Z |
format | Article |
id | doaj.art-ea06bbd69d1d4e3e9b2d2f38744ce07e |
institution | Directory Open Access Journal |
issn | 2227-9709 |
language | English |
last_indexed | 2024-04-12T22:10:19Z |
publishDate | 2018-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Informatics |
spelling | doaj.art-ea06bbd69d1d4e3e9b2d2f38744ce07e2022-12-22T03:14:47ZengMDPI AGInformatics2227-97092018-11-01544510.3390/informatics5040045informatics5040045Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer ReviewsNoor Rizvana Ahamed Kabeer0Keng Hoon Gan1Erum Haris2School of Computer Sciences, Universiti Sains Malaysia, Penang 11800, MalaysiaSchool of Computer Sciences, Universiti Sains Malaysia, Penang 11800, MalaysiaSchool of Computer Sciences, Universiti Sains Malaysia, Penang 11800, MalaysiaOnline reviews are an important source of opinion to measure products’ quality. Hence, automated opinion mining is used to extract important features (aspect) and related comments (sentiment). Extraction of correct aspect-sentiment pairs is critical for overall outcome of opinion mining; however, current works still have limitations in terms of identifying special compound noun and parent-child relationship aspects in the extraction process. To address these problems, an aspect-sentiment pair extraction using the rules and compound noun lexicon (ASPERC) model is proposed. The model consists of three main phases, such as compound noun lexicon generation, aspect-sentiment pair rule generation, and aspect-sentiment pair extraction. The combined approach of rules generated from training sentences and domain specific compound noun lexicon enable extraction of more aspects by firstly identifying special compound noun and parent-child aspects, which eventually contribute to more aspect-sentiment pair extraction. The experiment is conducted with the SemEval 2014 dataset to compare proposed and baseline models. Both ASPERC and its variant, ASPER, result higher in recall (28.58% and 22.55% each) compared to baseline and satisfactorily extract more aspect sentiment pairs. Lastly, the reasonable outcome of ASPER indicates applicability of rules to various domains.https://www.mdpi.com/2227-9709/5/4/45aspect extractionsentiment extractionlexiconopinion miningrule-basedsentiment analysis |
spellingShingle | Noor Rizvana Ahamed Kabeer Keng Hoon Gan Erum Haris Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews Informatics aspect extraction sentiment extraction lexicon opinion mining rule-based sentiment analysis |
title | Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews |
title_full | Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews |
title_fullStr | Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews |
title_full_unstemmed | Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews |
title_short | Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews |
title_sort | domain specific aspect sentiment pair extraction using rules and compound noun lexicon for customer reviews |
topic | aspect extraction sentiment extraction lexicon opinion mining rule-based sentiment analysis |
url | https://www.mdpi.com/2227-9709/5/4/45 |
work_keys_str_mv | AT noorrizvanaahamedkabeer domainspecificaspectsentimentpairextractionusingrulesandcompoundnounlexiconforcustomerreviews AT kenghoongan domainspecificaspectsentimentpairextractionusingrulesandcompoundnounlexiconforcustomerreviews AT erumharis domainspecificaspectsentimentpairextractionusingrulesandcompoundnounlexiconforcustomerreviews |