Weighted multi-label classification model for sentiment analysis of online news

Xin LI; Haoran XIE; Yanghui RAO; Yanjia CHEN; Xuebo LIU; Huan HUANG; Fu Lee WANG

doi:10.1109/BIGCOMP.2016.7425916

Weighted multi-label classification model for sentiment analysis of online news

Xin LI, Haoran XIE, Yanghui RAO^*, Yanjia CHEN, Xuebo LIU, Huan HUANG, Fu Lee WANG

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

32 Citations (Scopus)

Abstract

With the extensive growth of social media services, many users express their feelings and opinions through news articles, blogs and tweets/microblogs. To discover the connections between emotions evoked in a user by varied-scale documents effectively, the paper is concerned with the problem of sentiment analysis over online news. Different from previous models which treat training documents uniformly, a weighted multi-label classification model (WMCM) is proposed by introducing the concept of emotional concentration to estimate the weight of training documents, in addition to tackle the issue of noisy samples for each emotion. The topic assignment is also used to distinguish different emotional senses of the same word at the semantic level. Experimental evaluations using short news headlines and long documents validate the effectiveness of the proposed WMCM for sentiment prediction.

Original language	English
Title of host publication	2016 International Conference on Big Data and Smart Computing, BigComp 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	215-222
Number of pages	8
ISBN (Electronic)	9781467387965
DOIs	https://doi.org/10.1109/BIGCOMP.2016.7425916
Publication status	Published - 3 Mar 2016
Externally published	Yes
Event	International Conference on Big Data and Smart Computing, BigComp 2016 - Hong Kong, China Duration: 18 Jan 2016 → 20 Jan 2016

Publication series

Name	2016 International Conference on Big Data and Smart Computing, BigComp 2016

Conference

Conference	International Conference on Big Data and Smart Computing, BigComp 2016
Country/Territory	China
City	Hong Kong
Period	18/01/16 → 20/01/16

Funding

The authors are thankful to the anonymous reviewers for their constructive comments and suggestions on an earlier version of this paper. The research described in this paper has been supported by the National Natural Science Foundation of China (Grant No. 61502545), a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (Grant No. UGC/FDS11/E06/14), and "the Fundamental Research Funds for the Central Universities" (Grant No. 46000-31610009).

Keywords

Emotional concentration
Multi-label classification
Sentiment analysis

Access to Document

10.1109/BIGCOMP.2016.7425916

Cite this

LI, X., XIE, H., RAO, Y., CHEN, Y., LIU, X., HUANG, H., & WANG, F. L. (2016). Weighted multi-label classification model for sentiment analysis of online news. In 2016 International Conference on Big Data and Smart Computing, BigComp 2016 (pp. 215-222). Article 7425916 (2016 International Conference on Big Data and Smart Computing, BigComp 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIGCOMP.2016.7425916

@inproceedings{610c0426c9574281aa41edf1de5e9b96,

title = "Weighted multi-label classification model for sentiment analysis of online news",

abstract = "With the extensive growth of social media services, many users express their feelings and opinions through news articles, blogs and tweets/microblogs. To discover the connections between emotions evoked in a user by varied-scale documents effectively, the paper is concerned with the problem of sentiment analysis over online news. Different from previous models which treat training documents uniformly, a weighted multi-label classification model (WMCM) is proposed by introducing the concept of emotional concentration to estimate the weight of training documents, in addition to tackle the issue of noisy samples for each emotion. The topic assignment is also used to distinguish different emotional senses of the same word at the semantic level. Experimental evaluations using short news headlines and long documents validate the effectiveness of the proposed WMCM for sentiment prediction.",

keywords = "Emotional concentration, Multi-label classification, Sentiment analysis",

author = "Xin LI and Haoran XIE and Yanghui RAO and Yanjia CHEN and Xuebo LIU and Huan HUANG and WANG, {Fu Lee}",

year = "2016",

month = mar,

day = "3",

doi = "10.1109/BIGCOMP.2016.7425916",

language = "English",

series = "2016 International Conference on Big Data and Smart Computing, BigComp 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "215--222",

booktitle = "2016 International Conference on Big Data and Smart Computing, BigComp 2016",

address = "United States",

note = "International Conference on Big Data and Smart Computing, BigComp 2016 ; Conference date: 18-01-2016 Through 20-01-2016",

}

LI, X, XIE, H, RAO, Y, CHEN, Y, LIU, X, HUANG, H & WANG, FL 2016, Weighted multi-label classification model for sentiment analysis of online news. in 2016 International Conference on Big Data and Smart Computing, BigComp 2016., 7425916, 2016 International Conference on Big Data and Smart Computing, BigComp 2016, Institute of Electrical and Electronics Engineers Inc., pp. 215-222, International Conference on Big Data and Smart Computing, BigComp 2016, Hong Kong, China, 18/01/16. https://doi.org/10.1109/BIGCOMP.2016.7425916

Weighted multi-label classification model for sentiment analysis of online news. / LI, Xin; XIE, Haoran; RAO, Yanghui et al.
2016 International Conference on Big Data and Smart Computing, BigComp 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 215-222 7425916 (2016 International Conference on Big Data and Smart Computing, BigComp 2016).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Weighted multi-label classification model for sentiment analysis of online news

AU - LI, Xin

AU - XIE, Haoran

AU - RAO, Yanghui

AU - CHEN, Yanjia

AU - LIU, Xuebo

AU - HUANG, Huan

AU - WANG, Fu Lee

PY - 2016/3/3

Y1 - 2016/3/3

N2 - With the extensive growth of social media services, many users express their feelings and opinions through news articles, blogs and tweets/microblogs. To discover the connections between emotions evoked in a user by varied-scale documents effectively, the paper is concerned with the problem of sentiment analysis over online news. Different from previous models which treat training documents uniformly, a weighted multi-label classification model (WMCM) is proposed by introducing the concept of emotional concentration to estimate the weight of training documents, in addition to tackle the issue of noisy samples for each emotion. The topic assignment is also used to distinguish different emotional senses of the same word at the semantic level. Experimental evaluations using short news headlines and long documents validate the effectiveness of the proposed WMCM for sentiment prediction.

AB - With the extensive growth of social media services, many users express their feelings and opinions through news articles, blogs and tweets/microblogs. To discover the connections between emotions evoked in a user by varied-scale documents effectively, the paper is concerned with the problem of sentiment analysis over online news. Different from previous models which treat training documents uniformly, a weighted multi-label classification model (WMCM) is proposed by introducing the concept of emotional concentration to estimate the weight of training documents, in addition to tackle the issue of noisy samples for each emotion. The topic assignment is also used to distinguish different emotional senses of the same word at the semantic level. Experimental evaluations using short news headlines and long documents validate the effectiveness of the proposed WMCM for sentiment prediction.

KW - Emotional concentration

KW - Multi-label classification

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=84964680938&partnerID=8YFLogxK

U2 - 10.1109/BIGCOMP.2016.7425916

DO - 10.1109/BIGCOMP.2016.7425916

M3 - Conference paper (refereed)

AN - SCOPUS:84964680938

T3 - 2016 International Conference on Big Data and Smart Computing, BigComp 2016

SP - 215

EP - 222

BT - 2016 International Conference on Big Data and Smart Computing, BigComp 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Conference on Big Data and Smart Computing, BigComp 2016

Y2 - 18 January 2016 through 20 January 2016

ER -

LI X, XIE H, RAO Y, CHEN Y, LIU X, HUANG H et al. Weighted multi-label classification model for sentiment analysis of online news. In 2016 International Conference on Big Data and Smart Computing, BigComp 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 215-222. 7425916. (2016 International Conference on Big Data and Smart Computing, BigComp 2016). doi: 10.1109/BIGCOMP.2016.7425916

Weighted multi-label classification model for sentiment analysis of online news

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this