Mining fine grained opinions by using probabilistic models and domain knowledge

Qingliang Miao, Qiudan Li, Dajun Zeng

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

19 Citations (Scopus)

Abstract

The explosive growth of the user-generated content on the Web has offered a rich data source for mining opinions. However, the large number of diverse review sources challenges the individual users and organizations on how to use the opinion information effectively. Therefore, automated opinion mining and summarization techniques have become increasingly important. Different from previous approaches that have mostly treated product feature and opinion extraction as two independent tasks, we merge them together in a unified process by using probabilistic models. Specifically, we treat the problem of product feature and opinion extraction as a sequence labeling task and adopt Conditional Random Fields models to accomplish it. As part of our work, we develop a computational approach to construct domain specific sentiment lexicon by combining semi-structured reviews with general sentiment lexicon, which helps to identify the sentiment orientations of opinions. Experimental results on two real world datasets show that the proposed method is effective.

Original languageEnglish (US)
Title of host publicationProceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010
Pages358-365
Number of pages8
Volume1
DOIs
StatePublished - 2010
Event2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010 - Toronto, ON, Canada
Duration: Aug 31 2010Sep 3 2010

Other

Other2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010
CountryCanada
CityToronto, ON
Period8/31/109/3/10

Fingerprint

Labeling
Statistical Models

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

Cite this

Miao, Q., Li, Q., & Zeng, D. (2010). Mining fine grained opinions by using probabilistic models and domain knowledge. In Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010 (Vol. 1, pp. 358-365). [5616605] https://doi.org/10.1109/WI-IAT.2010.193

Mining fine grained opinions by using probabilistic models and domain knowledge. / Miao, Qingliang; Li, Qiudan; Zeng, Dajun.

Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. Vol. 1 2010. p. 358-365 5616605.

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

Miao, Q, Li, Q & Zeng, D 2010, Mining fine grained opinions by using probabilistic models and domain knowledge. in Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. vol. 1, 5616605, pp. 358-365, 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010, Toronto, ON, Canada, 8/31/10. https://doi.org/10.1109/WI-IAT.2010.193
Miao Q, Li Q, Zeng D. Mining fine grained opinions by using probabilistic models and domain knowledge. In Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. Vol. 1. 2010. p. 358-365. 5616605 https://doi.org/10.1109/WI-IAT.2010.193
Miao, Qingliang ; Li, Qiudan ; Zeng, Dajun. / Mining fine grained opinions by using probabilistic models and domain knowledge. Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. Vol. 1 2010. pp. 358-365
@inproceedings{800298a4cc0e4c718b229aa6d00c7bea,
title = "Mining fine grained opinions by using probabilistic models and domain knowledge",
abstract = "The explosive growth of the user-generated content on the Web has offered a rich data source for mining opinions. However, the large number of diverse review sources challenges the individual users and organizations on how to use the opinion information effectively. Therefore, automated opinion mining and summarization techniques have become increasingly important. Different from previous approaches that have mostly treated product feature and opinion extraction as two independent tasks, we merge them together in a unified process by using probabilistic models. Specifically, we treat the problem of product feature and opinion extraction as a sequence labeling task and adopt Conditional Random Fields models to accomplish it. As part of our work, we develop a computational approach to construct domain specific sentiment lexicon by combining semi-structured reviews with general sentiment lexicon, which helps to identify the sentiment orientations of opinions. Experimental results on two real world datasets show that the proposed method is effective.",
author = "Qingliang Miao and Qiudan Li and Dajun Zeng",
year = "2010",
doi = "10.1109/WI-IAT.2010.193",
language = "English (US)",
isbn = "9780769541914",
volume = "1",
pages = "358--365",
booktitle = "Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010",

}

TY - GEN

T1 - Mining fine grained opinions by using probabilistic models and domain knowledge

AU - Miao, Qingliang

AU - Li, Qiudan

AU - Zeng, Dajun

PY - 2010

Y1 - 2010

N2 - The explosive growth of the user-generated content on the Web has offered a rich data source for mining opinions. However, the large number of diverse review sources challenges the individual users and organizations on how to use the opinion information effectively. Therefore, automated opinion mining and summarization techniques have become increasingly important. Different from previous approaches that have mostly treated product feature and opinion extraction as two independent tasks, we merge them together in a unified process by using probabilistic models. Specifically, we treat the problem of product feature and opinion extraction as a sequence labeling task and adopt Conditional Random Fields models to accomplish it. As part of our work, we develop a computational approach to construct domain specific sentiment lexicon by combining semi-structured reviews with general sentiment lexicon, which helps to identify the sentiment orientations of opinions. Experimental results on two real world datasets show that the proposed method is effective.

AB - The explosive growth of the user-generated content on the Web has offered a rich data source for mining opinions. However, the large number of diverse review sources challenges the individual users and organizations on how to use the opinion information effectively. Therefore, automated opinion mining and summarization techniques have become increasingly important. Different from previous approaches that have mostly treated product feature and opinion extraction as two independent tasks, we merge them together in a unified process by using probabilistic models. Specifically, we treat the problem of product feature and opinion extraction as a sequence labeling task and adopt Conditional Random Fields models to accomplish it. As part of our work, we develop a computational approach to construct domain specific sentiment lexicon by combining semi-structured reviews with general sentiment lexicon, which helps to identify the sentiment orientations of opinions. Experimental results on two real world datasets show that the proposed method is effective.

UR - http://www.scopus.com/inward/record.url?scp=78649861656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649861656&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2010.193

DO - 10.1109/WI-IAT.2010.193

M3 - Conference contribution

AN - SCOPUS:78649861656

SN - 9780769541914

VL - 1

SP - 358

EP - 365

BT - Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010

ER -