On the automatic learning of sentiment lexicons

Aliaksei Severyn, Alessandro Moschitti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

This paper describes a simple and principled approach to automatically construct sentiment lexicons using distant supervision. We induce the sentiment association scores for the lexicon items from a model trained on a weakly supervised corpora. Our empirical findings show that features extracted from such a machine-learned lexicon outperform models using manual or other automatically constructed sentiment lexicons. Finally, our system achieves the state-of-the-art in Twitter Sentiment Analysis tasks from Semeval-2013 and ranks 2nd best in Semeval-2014 according to the average rank.

Original languageEnglish
Title of host publicationNAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1397-1402
Number of pages6
ISBN (Print)9781941643495
Publication statusPublished - 2015
EventConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States
Duration: 31 May 20155 Jun 2015

Other

OtherConference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
CountryUnited States
CityDenver
Period31/5/155/6/15

Fingerprint

twitter
learning
supervision
Sentiment
Lexicon
Supervision

ASJC Scopus subject areas

  • Computer Science Applications
  • Language and Linguistics
  • Linguistics and Language

Cite this

Severyn, A., & Moschitti, A. (2015). On the automatic learning of sentiment lexicons. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1397-1402). Association for Computational Linguistics (ACL).

On the automatic learning of sentiment lexicons. / Severyn, Aliaksei; Moschitti, Alessandro.

NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 1397-1402.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Severyn, A & Moschitti, A 2015, On the automatic learning of sentiment lexicons. in NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 1397-1402, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, Denver, United States, 31/5/15.
Severyn A, Moschitti A. On the automatic learning of sentiment lexicons. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 1397-1402
Severyn, Aliaksei ; Moschitti, Alessandro. / On the automatic learning of sentiment lexicons. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 1397-1402
@inproceedings{e9d062aef6a84dd5bea1a56c36a32414,
title = "On the automatic learning of sentiment lexicons",
abstract = "This paper describes a simple and principled approach to automatically construct sentiment lexicons using distant supervision. We induce the sentiment association scores for the lexicon items from a model trained on a weakly supervised corpora. Our empirical findings show that features extracted from such a machine-learned lexicon outperform models using manual or other automatically constructed sentiment lexicons. Finally, our system achieves the state-of-the-art in Twitter Sentiment Analysis tasks from Semeval-2013 and ranks 2nd best in Semeval-2014 according to the average rank.",
author = "Aliaksei Severyn and Alessandro Moschitti",
year = "2015",
language = "English",
isbn = "9781941643495",
pages = "1397--1402",
booktitle = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - On the automatic learning of sentiment lexicons

AU - Severyn, Aliaksei

AU - Moschitti, Alessandro

PY - 2015

Y1 - 2015

N2 - This paper describes a simple and principled approach to automatically construct sentiment lexicons using distant supervision. We induce the sentiment association scores for the lexicon items from a model trained on a weakly supervised corpora. Our empirical findings show that features extracted from such a machine-learned lexicon outperform models using manual or other automatically constructed sentiment lexicons. Finally, our system achieves the state-of-the-art in Twitter Sentiment Analysis tasks from Semeval-2013 and ranks 2nd best in Semeval-2014 according to the average rank.

AB - This paper describes a simple and principled approach to automatically construct sentiment lexicons using distant supervision. We induce the sentiment association scores for the lexicon items from a model trained on a weakly supervised corpora. Our empirical findings show that features extracted from such a machine-learned lexicon outperform models using manual or other automatically constructed sentiment lexicons. Finally, our system achieves the state-of-the-art in Twitter Sentiment Analysis tasks from Semeval-2013 and ranks 2nd best in Semeval-2014 according to the average rank.

UR - http://www.scopus.com/inward/record.url?scp=84949865400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949865400&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84949865400

SN - 9781941643495

SP - 1397

EP - 1402

BT - NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -