Cognitive-inspired domain adaptation of sentiment lexicons

Sentiment lexicons are essential tools for polarity classification and opinion mining. In contrast to machine learning methods that only leverage text features or raw text for sentiment analysis, methods that use sentiment lexicons embrace higher interpretability. Although a number of domain-specifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Xing, Frank Z., Pallucchini, Filippo, Cambria, Erik
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/151125
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-151125
record_format dspace
spelling sg-ntu-dr.10356-1511252021-06-24T10:11:52Z Cognitive-inspired domain adaptation of sentiment lexicons Xing, Frank Z. Pallucchini, Filippo Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Sentiment Lexicon Domain Adaptation Sentiment lexicons are essential tools for polarity classification and opinion mining. In contrast to machine learning methods that only leverage text features or raw text for sentiment analysis, methods that use sentiment lexicons embrace higher interpretability. Although a number of domain-specific sentiment lexicons are made available, it is impractical to build an ex ante lexicon that fully reflects the characteristics of the language usage in endless domains. In this article, we propose a novel approach to simultaneously train a vanilla sentiment classifier and adapt word polarities to the target domain. Specifically, we sequentially track the wrongly predicted sentences and use them as the supervision instead of addressing the gold standard as a whole to emulate the life-long cognitive process of lexicon learning. An exploration-exploitation mechanism is designed to trade off between searching for new sentiment words and updating the polarity score of one word. Experimental results on several popular datasets show that our approach significantly improves the sentiment classification performance for a variety of domains by means of improving the quality of sentiment lexicons. Case-studies also illustrate how polarity scores of the same words are discovered for different domains. 2021-06-24T10:11:52Z 2021-06-24T10:11:52Z 2019 Journal Article Xing, F. Z., Pallucchini, F. & Cambria, E. (2019). Cognitive-inspired domain adaptation of sentiment lexicons. Information Processing and Management, 56(3), 554-564. https://dx.doi.org/10.1016/j.ipm.2018.11.002 0306-4573 0000-0002-5751-3937 0000-0002-3030-1280 https://hdl.handle.net/10356/151125 10.1016/j.ipm.2018.11.002 2-s2.0-85059608591 3 56 554 564 en Information Processing and Management © 2018 Elsevier Ltd. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Sentiment Lexicon
Domain Adaptation
spellingShingle Engineering::Computer science and engineering
Sentiment Lexicon
Domain Adaptation
Xing, Frank Z.
Pallucchini, Filippo
Cambria, Erik
Cognitive-inspired domain adaptation of sentiment lexicons
description Sentiment lexicons are essential tools for polarity classification and opinion mining. In contrast to machine learning methods that only leverage text features or raw text for sentiment analysis, methods that use sentiment lexicons embrace higher interpretability. Although a number of domain-specific sentiment lexicons are made available, it is impractical to build an ex ante lexicon that fully reflects the characteristics of the language usage in endless domains. In this article, we propose a novel approach to simultaneously train a vanilla sentiment classifier and adapt word polarities to the target domain. Specifically, we sequentially track the wrongly predicted sentences and use them as the supervision instead of addressing the gold standard as a whole to emulate the life-long cognitive process of lexicon learning. An exploration-exploitation mechanism is designed to trade off between searching for new sentiment words and updating the polarity score of one word. Experimental results on several popular datasets show that our approach significantly improves the sentiment classification performance for a variety of domains by means of improving the quality of sentiment lexicons. Case-studies also illustrate how polarity scores of the same words are discovered for different domains.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Xing, Frank Z.
Pallucchini, Filippo
Cambria, Erik
format Article
author Xing, Frank Z.
Pallucchini, Filippo
Cambria, Erik
author_sort Xing, Frank Z.
title Cognitive-inspired domain adaptation of sentiment lexicons
title_short Cognitive-inspired domain adaptation of sentiment lexicons
title_full Cognitive-inspired domain adaptation of sentiment lexicons
title_fullStr Cognitive-inspired domain adaptation of sentiment lexicons
title_full_unstemmed Cognitive-inspired domain adaptation of sentiment lexicons
title_sort cognitive-inspired domain adaptation of sentiment lexicons
publishDate 2021
url https://hdl.handle.net/10356/151125
_version_ 1703971151172075520