Using Pivot-Based Paraphrasing and Sentiment Profiles to Improve a Subjectivity Lexicon for Essay Data

Beata Beigman Klebanov, Nitin Madnani, Jill Burstein


Abstract
We demonstrate a method of improving a seed sentiment lexicon developed on essay data by using a pivot-based paraphrasing system for lexical expansion coupled with sentiment profile enrichment using crowdsourcing. Profile enrichment alone yields up to 15% improvement in the accuracy of the seed lexicon on 3-way sentence-level sentiment polarity classification of essay data. Using lexical expansion in addition to sentiment profiles provides a further 7% improvement in performance. Additional experiments show that the proposed method is also effective with other subjectivity lexicons and in a different domain of application (product reviews).
Anthology ID:
Q13-1009
Volume:
Transactions of the Association for Computational Linguistics, Volume 1
Month:
Year:
2013
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
99–110
Language:
URL:
https://aclanthology.org/Q13-1009
DOI:
10.1162/tacl_a_00213
Bibkey:
Cite (ACL):
Beata Beigman Klebanov, Nitin Madnani, and Jill Burstein. 2013. Using Pivot-Based Paraphrasing and Sentiment Profiles to Improve a Subjectivity Lexicon for Essay Data. Transactions of the Association for Computational Linguistics, 1:99–110.
Cite (Informal):
Using Pivot-Based Paraphrasing and Sentiment Profiles to Improve a Subjectivity Lexicon for Essay Data (Beigman Klebanov et al., TACL 2013)
Copy Citation:
PDF:
https://aclanthology.org/Q13-1009.pdf