Learning knowledge from relevant webpage for opinion analysis

Ruifeng Xu; Kam Fai Wong; Qin Lu; Yunqing Xia; Wenjie Li

doi:10.1109/WIIAT.2008.388

Learning knowledge from relevant webpage for opinion analysis

Ruifeng Xu, Kam Fai Wong, Qin Lu, Yunqing Xia, Wenjie Li

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

21 Citations (Scopus)

Abstract

T This paper presents an opinion analysis system based on linguistic knowledge which is acquired from small-scale annotated text and raw topic-relevant webpage. Based on the observation on the annotated opinion corpus, some word-, collocation-and sentence-level linguistic features for opinion analysis are discovered. Supervised and unsupervised learning techniques are developed to learn these features from annotated text and raw relevant webpage, respectively. These features are then incorporated into a support vector machine based classifier to identify opinionated sentences from running text and determine their polarities. Evaluations show that the proposed opinion analysis system, namely OA, achieved promising performance, which shows the effectiveness of linguistic knowledge learning from relevant webpage.

Original language	English
Title of host publication	Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008
Pages	307-313
Number of pages	7
DOIs	https://doi.org/10.1109/WIIAT.2008.388
Publication status	Published - 1 Dec 2008
Event	2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008 - Sydney, NSW, Australia Duration: 9 Dec 2008 → 12 Dec 2008

Conference

Conference	2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008
Country/Territory	Australia
City	Sydney, NSW
Period	9/12/08 → 12/12/08

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Electrical and Electronic Engineering

More information

10.1109/WIIAT.2008.388

Cite this

@inproceedings{5e84cc4d4f524a5b88c3a14e690f71ab,

title = "Learning knowledge from relevant webpage for opinion analysis",

abstract = "T This paper presents an opinion analysis system based on linguistic knowledge which is acquired from small-scale annotated text and raw topic-relevant webpage. Based on the observation on the annotated opinion corpus, some word-, collocation-and sentence-level linguistic features for opinion analysis are discovered. Supervised and unsupervised learning techniques are developed to learn these features from annotated text and raw relevant webpage, respectively. These features are then incorporated into a support vector machine based classifier to identify opinionated sentences from running text and determine their polarities. Evaluations show that the proposed opinion analysis system, namely OA, achieved promising performance, which shows the effectiveness of linguistic knowledge learning from relevant webpage.",

author = "Ruifeng Xu and Wong, {Kam Fai} and Qin Lu and Yunqing Xia and Wenjie Li",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/WIIAT.2008.388",

language = "English",

isbn = "9780769534961",

pages = "307--313",

booktitle = "Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008",

note = "2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008 ; Conference date: 09-12-2008 Through 12-12-2008",

}

TY - GEN

T1 - Learning knowledge from relevant webpage for opinion analysis

AU - Xu, Ruifeng

AU - Wong, Kam Fai

AU - Lu, Qin

AU - Xia, Yunqing

AU - Li, Wenjie

PY - 2008/12/1

Y1 - 2008/12/1

N2 - T This paper presents an opinion analysis system based on linguistic knowledge which is acquired from small-scale annotated text and raw topic-relevant webpage. Based on the observation on the annotated opinion corpus, some word-, collocation-and sentence-level linguistic features for opinion analysis are discovered. Supervised and unsupervised learning techniques are developed to learn these features from annotated text and raw relevant webpage, respectively. These features are then incorporated into a support vector machine based classifier to identify opinionated sentences from running text and determine their polarities. Evaluations show that the proposed opinion analysis system, namely OA, achieved promising performance, which shows the effectiveness of linguistic knowledge learning from relevant webpage.

AB - T This paper presents an opinion analysis system based on linguistic knowledge which is acquired from small-scale annotated text and raw topic-relevant webpage. Based on the observation on the annotated opinion corpus, some word-, collocation-and sentence-level linguistic features for opinion analysis are discovered. Supervised and unsupervised learning techniques are developed to learn these features from annotated text and raw relevant webpage, respectively. These features are then incorporated into a support vector machine based classifier to identify opinionated sentences from running text and determine their polarities. Evaluations show that the proposed opinion analysis system, namely OA, achieved promising performance, which shows the effectiveness of linguistic knowledge learning from relevant webpage.

UR - http://www.scopus.com/inward/record.url?scp=62949127524&partnerID=8YFLogxK

U2 - 10.1109/WIIAT.2008.388

DO - 10.1109/WIIAT.2008.388

M3 - Conference article published in proceeding or book

SN - 9780769534961

SP - 307

EP - 313

BT - Proceedings - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008

T2 - 2008 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2008

Y2 - 9 December 2008 through 12 December 2008

ER -

Learning knowledge from relevant webpage for opinion analysis

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this