Topic-specific sentiment analysis can help identify political ideology

Sumit Bhatia; Deepak Padmanabhan

Topic-specific sentiment analysis can help identify political ideology

Sumit Bhatia
, Deepak Padmanabhan

School of Electronics, Electrical Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Citations (Scopus)

241 Downloads (Pure)

Abstract

Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues. We propose a simple framework that represents a political ideology as a distribution of sentiment polarities towards a set of topics. This representation can then be used to detect ideological leanings of documents (speeches, news articles, etc.) based on the sentiments expressed towards different topics. Experiments performed using a widely used dataset show the promise of our proposed approach that achieves comparable performance to other methods despite being much simpler and more interpretable.

Original language	English
Title of host publication	Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
Pages	79-84
Publication status	Published - 31 Oct 2018
Event	Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis - Brussels, Belgium Duration: 01 Nov 2018 → … https://wt-public.emm4u.eu/wassa2018/

Workshop

Workshop	Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
Abbreviated title	WASSA 2018
Country/Territory	Belgium
City	Brussels
Period	01/11/2018 → …
Internet address	https://wt-public.emm4u.eu/wassa2018/

Access to Document

Topic-specific sentiment analysis can help identify political ideology
© 2018 The Association for Computational Linguistics. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Final published version, 223 KBLicence: Unspecified

http://aclweb.org/anthology/W18-6212 Licence: Unspecified

Cite this

@inproceedings{6539c915cb4f4072ba7aaf542435daa5,

title = "Topic-specific sentiment analysis can help identify political ideology",

abstract = "Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues. We propose a simple framework that represents a political ideology as a distribution of sentiment polarities towards a set of topics. This representation can then be used to detect ideological leanings of documents (speeches, news articles, etc.) based on the sentiments expressed towards different topics. Experiments performed using a widely used dataset show the promise of our proposed approach that achieves comparable performance to other methods despite being much simpler and more interpretable.",

author = "Sumit Bhatia and Deepak Padmanabhan",

year = "2018",

month = oct,

day = "31",

language = "English",

isbn = "978-1-948087-80-3",

pages = "79--84",

booktitle = "Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment \& Social Media Analysis",

note = "Workshop on Computational Approaches to Subjectivity, Sentiment \& Social Media Analysis, WASSA 2018 ; Conference date: 01-11-2018",

url = "https://wt-public.emm4u.eu/wassa2018/",

}

Bhatia, S & Padmanabhan, D 2018, Topic-specific sentiment analysis can help identify political ideology. in Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis. pp. 79-84, Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, Brussels, Belgium, 01/11/2018. <http://aclweb.org/anthology/W18-6212 >

TY - GEN

T1 - Topic-specific sentiment analysis can help identify political ideology

AU - Bhatia, Sumit

AU - Padmanabhan, Deepak

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues. We propose a simple framework that represents a political ideology as a distribution of sentiment polarities towards a set of topics. This representation can then be used to detect ideological leanings of documents (speeches, news articles, etc.) based on the sentiments expressed towards different topics. Experiments performed using a widely used dataset show the promise of our proposed approach that achieves comparable performance to other methods despite being much simpler and more interpretable.

AB - Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues. We propose a simple framework that represents a political ideology as a distribution of sentiment polarities towards a set of topics. This representation can then be used to detect ideological leanings of documents (speeches, news articles, etc.) based on the sentiments expressed towards different topics. Experiments performed using a widely used dataset show the promise of our proposed approach that achieves comparable performance to other methods despite being much simpler and more interpretable.

M3 - Conference contribution

SN - 978-1-948087-80-3

SP - 79

EP - 84

BT - Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis

T2 - Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis

Y2 - 1 November 2018

ER -

Topic-specific sentiment analysis can help identify political ideology

Abstract

Workshop

Access to Document

Fingerprint

Cite this