2.50
Hdl Handle:
http://hdl.handle.net/2436/620737
Title:
A Machine-Learning Approach to Negation and Speculation Detection for Sentiment Analysis
Authors:
Cruz, Noa, P., Taboada, Maite., Mitkov, Ruslan.
Abstract:
Recognizing negative and speculative information is highly relevant for sentiment analysis. This paper presents a machine-learning approach to automatically detect this kind of information in the review domain. The resulting system works in two steps: in the first pass, negation/speculation cues are identified, and in the second phase the full scope of these cues is determined. The system is trained and evaluated on the Simon Fraser University Review corpus, which is extensively used in opinion mining. The results show how the proposed method outstrips the baseline by as much as roughly 20% in the negation cue detection and around 13% in the scope recognition, both in terms of F1. In speculation, the performance obtained in the cue prediction phase is close to that obtained by a human rater carrying out the same task. In the scope detection, the results are also promising and represent a substantial improvement on the baseline (up by roughly 10%). A detailed error analysis is also provided. The extrinsic evaluation shows that the correct identification of cues and scopes is vital for the task of sentiment analysis.
Journal:
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
Issue Date:
2015
URI:
http://hdl.handle.net/2436/620737
Type:
Article
Language:
en
Appears in Collections:
Computational Linguistics Group

Full metadata record

DC FieldValue Language
dc.contributor.authorCruz, Noa, P., Taboada, Maite., Mitkov, Ruslan.en
dc.date.accessioned2017-10-10T08:33:16Z-
dc.date.available2017-10-10T08:33:16Z-
dc.date.issued2015-
dc.identifier.urihttp://hdl.handle.net/2436/620737-
dc.description.abstractRecognizing negative and speculative information is highly relevant for sentiment analysis. This paper presents a machine-learning approach to automatically detect this kind of information in the review domain. The resulting system works in two steps: in the first pass, negation/speculation cues are identified, and in the second phase the full scope of these cues is determined. The system is trained and evaluated on the Simon Fraser University Review corpus, which is extensively used in opinion mining. The results show how the proposed method outstrips the baseline by as much as roughly 20% in the negation cue detection and around 13% in the scope recognition, both in terms of F1. In speculation, the performance obtained in the cue prediction phase is close to that obtained by a human rater carrying out the same task. In the scope detection, the results are also promising and represent a substantial improvement on the baseline (up by roughly 10%). A detailed error analysis is also provided. The extrinsic evaluation shows that the correct identification of cues and scopes is vital for the task of sentiment analysis.en
dc.language.isoenen
dc.subjectComputational Linguisticsen
dc.subjectMachine Learningen
dc.subjectSentiment Analysisen
dc.titleA Machine-Learning Approach to Negation and Speculation Detection for Sentiment Analysisen
dc.typeArticleen
dc.identifier.journalJOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGYen
All Items in WIRE are protected by copyright, with all rights reserved, unless otherwise indicated.