Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches

Piyoros Tungthamthiti, Kiyoaki Shirai, Masnizah Mohd

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

8 Citations (Scopus)

Abstract

Sarcasm is a form of communication that is intended to mock or harass someone by using words with the opposite of their literal meaning. However, identification of sarcasm is somewhat difficult due to the gap between its literal and intended meaning. Recognition of sarcasm is a task that can potentially provide a lot of benefits to other areas of natural language processing. In this research, we propose a new method to identify sarcasm in tweets that focuses on several approaches: 1) sentiment analysis, 2) concept level and common-sense knowledge 3) coherence and 4) machine learning classification. We will use support vector machine (SVM) to classify sarcastic tweet based on our proposed features as well as ordinary N-grams. Our proposed classifier is an ensemble of two SVMs with two different feature sets. The results of the experiment show our method outperforms the baseline method and achieves 80% accuracy.

Original languageEnglish
Title of host publicationProceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
PublisherFaculty of Pharmaceutical Sciences, Chulalongkorn University
Pages404-413
Number of pages10
ISBN (Electronic)9786165518871
Publication statusPublished - 2014
Externally publishedYes
Event28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 - Phuket, Thailand
Duration: 12 Dec 201414 Dec 2014

Other

Other28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
CountryThailand
CityPhuket
Period12/12/1414/12/14

Fingerprint

Supervised learning
Support vector machines
Learning systems
Classifiers
Communication
Processing
Experiments
Sarcasm
Sentiment

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)

Cite this

Tungthamthiti, P., Shirai, K., & Mohd, M. (2014). Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 (pp. 404-413). Faculty of Pharmaceutical Sciences, Chulalongkorn University.

Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches. / Tungthamthiti, Piyoros; Shirai, Kiyoaki; Mohd, Masnizah.

Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014. Faculty of Pharmaceutical Sciences, Chulalongkorn University, 2014. p. 404-413.

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

Tungthamthiti, P, Shirai, K & Mohd, M 2014, Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches. in Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014. Faculty of Pharmaceutical Sciences, Chulalongkorn University, pp. 404-413, 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014, Phuket, Thailand, 12/12/14.
Tungthamthiti P, Shirai K, Mohd M. Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014. Faculty of Pharmaceutical Sciences, Chulalongkorn University. 2014. p. 404-413
Tungthamthiti, Piyoros ; Shirai, Kiyoaki ; Mohd, Masnizah. / Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches. Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014. Faculty of Pharmaceutical Sciences, Chulalongkorn University, 2014. pp. 404-413
@inproceedings{e46325429cf245b58edc6f687b3aac1e,
title = "Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches",
abstract = "Sarcasm is a form of communication that is intended to mock or harass someone by using words with the opposite of their literal meaning. However, identification of sarcasm is somewhat difficult due to the gap between its literal and intended meaning. Recognition of sarcasm is a task that can potentially provide a lot of benefits to other areas of natural language processing. In this research, we propose a new method to identify sarcasm in tweets that focuses on several approaches: 1) sentiment analysis, 2) concept level and common-sense knowledge 3) coherence and 4) machine learning classification. We will use support vector machine (SVM) to classify sarcastic tweet based on our proposed features as well as ordinary N-grams. Our proposed classifier is an ensemble of two SVMs with two different feature sets. The results of the experiment show our method outperforms the baseline method and achieves 80{\%} accuracy.",
author = "Piyoros Tungthamthiti and Kiyoaki Shirai and Masnizah Mohd",
year = "2014",
language = "English",
pages = "404--413",
booktitle = "Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014",
publisher = "Faculty of Pharmaceutical Sciences, Chulalongkorn University",

}

TY - GEN

T1 - Recognition of sarcasm in tweets based on concept level sentiment analysis and supervised learning approaches

AU - Tungthamthiti, Piyoros

AU - Shirai, Kiyoaki

AU - Mohd, Masnizah

PY - 2014

Y1 - 2014

N2 - Sarcasm is a form of communication that is intended to mock or harass someone by using words with the opposite of their literal meaning. However, identification of sarcasm is somewhat difficult due to the gap between its literal and intended meaning. Recognition of sarcasm is a task that can potentially provide a lot of benefits to other areas of natural language processing. In this research, we propose a new method to identify sarcasm in tweets that focuses on several approaches: 1) sentiment analysis, 2) concept level and common-sense knowledge 3) coherence and 4) machine learning classification. We will use support vector machine (SVM) to classify sarcastic tweet based on our proposed features as well as ordinary N-grams. Our proposed classifier is an ensemble of two SVMs with two different feature sets. The results of the experiment show our method outperforms the baseline method and achieves 80% accuracy.

AB - Sarcasm is a form of communication that is intended to mock or harass someone by using words with the opposite of their literal meaning. However, identification of sarcasm is somewhat difficult due to the gap between its literal and intended meaning. Recognition of sarcasm is a task that can potentially provide a lot of benefits to other areas of natural language processing. In this research, we propose a new method to identify sarcasm in tweets that focuses on several approaches: 1) sentiment analysis, 2) concept level and common-sense knowledge 3) coherence and 4) machine learning classification. We will use support vector machine (SVM) to classify sarcastic tweet based on our proposed features as well as ordinary N-grams. Our proposed classifier is an ensemble of two SVMs with two different feature sets. The results of the experiment show our method outperforms the baseline method and achieves 80% accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84994130870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994130870&partnerID=8YFLogxK

M3 - Conference contribution

SP - 404

EP - 413

BT - Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014

PB - Faculty of Pharmaceutical Sciences, Chulalongkorn University

ER -