Sentiment analyzer with rich features for ironic and sarcastic tweets

Piyoros Tungthamthiti; Enrico Santus; Hongzhi Xu; Chu-ren Huang; Kiyoaki Shirai

Sentiment analyzer with rich features for ironic and sarcastic tweets

Piyoros Tungthamthiti, Enrico Santus, Hongzhi Xu, Chu-ren Huang, Kiyoaki Shirai

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

3 Citations (Scopus)

Abstract

Sentiment Analysis of tweets is a complex task, because these short messages employ unconventional language to increase the expressiveness. This task becomes even more difficult when people use figurative language (e.g. irony, sarcasm and metaphors) because it causes a mismatch between the literal meaning and the actual expressed sentiment. In this paper, we describe a sentiment analysis system designed for handling ironic and sarcastic tweets. Features grounded on several linguistic levels are proposed and used to classify the tweets in a 11-scale range, using a decision tree. The system is evaluated on the dataset released by the organizers of the SemEval 2015, task 11. The results show that our method largely outperforms the systems proposed by the participants of the task on ironic and sarcastic tweets.

Original language	English
Title of host publication	29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015
Publisher	Shanghai Jiao Tong University
Pages	178-187
Number of pages	10
Publication status	Published - 1 Jan 2015
Event	29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 - Shanghai, China Duration: 30 Oct 2015 → 1 Nov 2015

Conference

Conference	29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015
Country/Territory	China
City	Shanghai
Period	30/10/15 → 1/11/15

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Linguistics and Language

Cite this

@inproceedings{f8345d3e39f241af915d8e853fde3869,

title = "Sentiment analyzer with rich features for ironic and sarcastic tweets",

abstract = "Sentiment Analysis of tweets is a complex task, because these short messages employ unconventional language to increase the expressiveness. This task becomes even more difficult when people use figurative language (e.g. irony, sarcasm and metaphors) because it causes a mismatch between the literal meaning and the actual expressed sentiment. In this paper, we describe a sentiment analysis system designed for handling ironic and sarcastic tweets. Features grounded on several linguistic levels are proposed and used to classify the tweets in a 11-scale range, using a decision tree. The system is evaluated on the dataset released by the organizers of the SemEval 2015, task 11. The results show that our method largely outperforms the systems proposed by the participants of the task on ironic and sarcastic tweets.",

author = "Piyoros Tungthamthiti and Enrico Santus and Hongzhi Xu and Chu-ren Huang and Kiyoaki Shirai",

year = "2015",

month = jan,

day = "1",

language = "English",

pages = "178--187",

booktitle = "29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015",

publisher = "Shanghai Jiao Tong University",

address = "China",

note = "29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 ; Conference date: 30-10-2015 Through 01-11-2015",

}

Tungthamthiti, P, Santus, E, Xu, H, Huang, C & Shirai, K 2015, Sentiment analyzer with rich features for ironic and sarcastic tweets. in 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015. Shanghai Jiao Tong University, pp. 178-187, 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015, Shanghai, China, 30/10/15.

Sentiment analyzer with rich features for ironic and sarcastic tweets. / Tungthamthiti, Piyoros; Santus, Enrico; Xu, Hongzhi et al.

29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015. Shanghai Jiao Tong University, 2015. p. 178-187.

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

TY - GEN

T1 - Sentiment analyzer with rich features for ironic and sarcastic tweets

AU - Tungthamthiti, Piyoros

AU - Santus, Enrico

AU - Xu, Hongzhi

AU - Huang, Chu-ren

AU - Shirai, Kiyoaki

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Sentiment Analysis of tweets is a complex task, because these short messages employ unconventional language to increase the expressiveness. This task becomes even more difficult when people use figurative language (e.g. irony, sarcasm and metaphors) because it causes a mismatch between the literal meaning and the actual expressed sentiment. In this paper, we describe a sentiment analysis system designed for handling ironic and sarcastic tweets. Features grounded on several linguistic levels are proposed and used to classify the tweets in a 11-scale range, using a decision tree. The system is evaluated on the dataset released by the organizers of the SemEval 2015, task 11. The results show that our method largely outperforms the systems proposed by the participants of the task on ironic and sarcastic tweets.

AB - Sentiment Analysis of tweets is a complex task, because these short messages employ unconventional language to increase the expressiveness. This task becomes even more difficult when people use figurative language (e.g. irony, sarcasm and metaphors) because it causes a mismatch between the literal meaning and the actual expressed sentiment. In this paper, we describe a sentiment analysis system designed for handling ironic and sarcastic tweets. Features grounded on several linguistic levels are proposed and used to classify the tweets in a 11-scale range, using a decision tree. The system is evaluated on the dataset released by the organizers of the SemEval 2015, task 11. The results show that our method largely outperforms the systems proposed by the participants of the task on ironic and sarcastic tweets.

UR - http://www.scopus.com/inward/record.url?scp=84967204268&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 178

EP - 187

BT - 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015

PB - Shanghai Jiao Tong University

T2 - 29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015

Y2 - 30 October 2015 through 1 November 2015

ER -

Sentiment analyzer with rich features for ironic and sarcastic tweets

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this