A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs

Hung-Yu Kao, Zi Yu Lin

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

7 Citations (Scopus)

Abstract

In the past, there have been many documents focusing on English reviews for sentiment analysis. These contain abundant research results which extract features and opinions, identify semantic orientation, and associate features with opinions. Although this approach has performed well for English reviews, it is not as successful with Chinese reviews. In this paper, we aim to develop a sentiment analysis system that is suitable for Chinese reviews. This system would extract features that users are interested in and detect those opinions with semantic orientations that accord with the dependency of certain features and opinions in one specific category. We then present users with the integrated results. Our experiments show that the derived system can effectively measure the dependency between features and opinions. The prominent performance of review sentiment analysis also validates the applicability of the proposed method.

Original languageEnglish
Title of host publication2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010
Pages456-459
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 13
Event2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010 - Toronto, ON, Canada
Duration: 2010 Aug 312010 Sep 3

Publication series

NameProceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010
Volume1

Other

Other2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010
CountryCanada
CityToronto, ON
Period10-08-3110-09-03

Fingerprint

Blogs
Semantics
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

Cite this

Kao, H-Y., & Lin, Z. Y. (2010). A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs. In 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010 (pp. 456-459). [5616674] (Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010; Vol. 1). https://doi.org/10.1109/WI-IAT.2010.298
Kao, Hung-Yu ; Lin, Zi Yu. / A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs. 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. 2010. pp. 456-459 (Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010).
@inproceedings{60d082132fb842d3ae5a3d18b2fca9d9,
title = "A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs",
abstract = "In the past, there have been many documents focusing on English reviews for sentiment analysis. These contain abundant research results which extract features and opinions, identify semantic orientation, and associate features with opinions. Although this approach has performed well for English reviews, it is not as successful with Chinese reviews. In this paper, we aim to develop a sentiment analysis system that is suitable for Chinese reviews. This system would extract features that users are interested in and detect those opinions with semantic orientations that accord with the dependency of certain features and opinions in one specific category. We then present users with the integrated results. Our experiments show that the derived system can effectively measure the dependency between features and opinions. The prominent performance of review sentiment analysis also validates the applicability of the proposed method.",
author = "Hung-Yu Kao and Lin, {Zi Yu}",
year = "2010",
month = "12",
day = "13",
doi = "10.1109/WI-IAT.2010.298",
language = "English",
isbn = "9780769541914",
series = "Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010",
pages = "456--459",
booktitle = "2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010",

}

Kao, H-Y & Lin, ZY 2010, A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs. in 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010., 5616674, Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010, vol. 1, pp. 456-459, 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010, Toronto, ON, Canada, 10-08-31. https://doi.org/10.1109/WI-IAT.2010.298

A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs. / Kao, Hung-Yu; Lin, Zi Yu.

2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. 2010. p. 456-459 5616674 (Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010; Vol. 1).

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

TY - GEN

T1 - A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs

AU - Kao, Hung-Yu

AU - Lin, Zi Yu

PY - 2010/12/13

Y1 - 2010/12/13

N2 - In the past, there have been many documents focusing on English reviews for sentiment analysis. These contain abundant research results which extract features and opinions, identify semantic orientation, and associate features with opinions. Although this approach has performed well for English reviews, it is not as successful with Chinese reviews. In this paper, we aim to develop a sentiment analysis system that is suitable for Chinese reviews. This system would extract features that users are interested in and detect those opinions with semantic orientations that accord with the dependency of certain features and opinions in one specific category. We then present users with the integrated results. Our experiments show that the derived system can effectively measure the dependency between features and opinions. The prominent performance of review sentiment analysis also validates the applicability of the proposed method.

AB - In the past, there have been many documents focusing on English reviews for sentiment analysis. These contain abundant research results which extract features and opinions, identify semantic orientation, and associate features with opinions. Although this approach has performed well for English reviews, it is not as successful with Chinese reviews. In this paper, we aim to develop a sentiment analysis system that is suitable for Chinese reviews. This system would extract features that users are interested in and detect those opinions with semantic orientations that accord with the dependency of certain features and opinions in one specific category. We then present users with the integrated results. Our experiments show that the derived system can effectively measure the dependency between features and opinions. The prominent performance of review sentiment analysis also validates the applicability of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=78649885983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649885983&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2010.298

DO - 10.1109/WI-IAT.2010.298

M3 - Conference contribution

AN - SCOPUS:78649885983

SN - 9780769541914

T3 - Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010

SP - 456

EP - 459

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

ER -

Kao H-Y, Lin ZY. A categorized sentiment analysis of Chinese reviews by mining dependency in product features and opinions from blogs. In 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010. 2010. p. 456-459. 5616674. (Proceedings - 2010 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2010). https://doi.org/10.1109/WI-IAT.2010.298