A Pattern-Based Approach for Sarcasm Detection on Twitter

Mondher Bouazizi, Tomoaki Ohtsuki

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Sarcasm is a sophisticated form of irony widely used in social networks and microblogging websites. It is usually used to convey implicit information within the message a person transmits. Sarcasm might be used for different purposes, such as criticism or mockery. However, it is hard even for humans to recognize. Therefore, recognizing sarcastic statements can be very useful to improve automatic sentiment analysis of data collected from microblogging websites or social networks. Sentiment Analysis refers to the identification and aggregation of attitudes and opinions expressed by Internet users toward a specific topic. In this paper, we propose a pattern-based approach to detect sarcasm on Twitter. We propose four sets of features that cover the different types of sarcasm we defined. We use those to classify tweets as sarcastic and non-sarcastic. Our proposed approach reaches an accuracy of 83.1% with a precision equal to 91.1%. We also study the importance of each of the proposed sets of features and evaluate its added value to the classification. In particular, we emphasize the importance of pattern-based features for the detection of sarcastic statements.

Original languageEnglish
Article number7549041
Pages (from-to)5477-5488
Number of pages12
JournalIEEE Access
Volume4
DOIs
Publication statusPublished - 2016

Fingerprint

Websites
Agglomeration
Internet

Keywords

  • machine learning
  • sarcasm detection
  • sentiment analysis
  • Twitter

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

A Pattern-Based Approach for Sarcasm Detection on Twitter. / Bouazizi, Mondher; Ohtsuki, Tomoaki.

In: IEEE Access, Vol. 4, 7549041, 2016, p. 5477-5488.

Research output: Contribution to journalArticle

Bouazizi, Mondher ; Ohtsuki, Tomoaki. / A Pattern-Based Approach for Sarcasm Detection on Twitter. In: IEEE Access. 2016 ; Vol. 4. pp. 5477-5488.
@article{3587b165f5684c3793ae3739fd47ef7c,
title = "A Pattern-Based Approach for Sarcasm Detection on Twitter",
abstract = "Sarcasm is a sophisticated form of irony widely used in social networks and microblogging websites. It is usually used to convey implicit information within the message a person transmits. Sarcasm might be used for different purposes, such as criticism or mockery. However, it is hard even for humans to recognize. Therefore, recognizing sarcastic statements can be very useful to improve automatic sentiment analysis of data collected from microblogging websites or social networks. Sentiment Analysis refers to the identification and aggregation of attitudes and opinions expressed by Internet users toward a specific topic. In this paper, we propose a pattern-based approach to detect sarcasm on Twitter. We propose four sets of features that cover the different types of sarcasm we defined. We use those to classify tweets as sarcastic and non-sarcastic. Our proposed approach reaches an accuracy of 83.1{\%} with a precision equal to 91.1{\%}. We also study the importance of each of the proposed sets of features and evaluate its added value to the classification. In particular, we emphasize the importance of pattern-based features for the detection of sarcastic statements.",
keywords = "machine learning, sarcasm detection, sentiment analysis, Twitter",
author = "Mondher Bouazizi and Tomoaki Ohtsuki",
year = "2016",
doi = "10.1109/ACCESS.2016.2594194",
language = "English",
volume = "4",
pages = "5477--5488",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A Pattern-Based Approach for Sarcasm Detection on Twitter

AU - Bouazizi, Mondher

AU - Ohtsuki, Tomoaki

PY - 2016

Y1 - 2016

N2 - Sarcasm is a sophisticated form of irony widely used in social networks and microblogging websites. It is usually used to convey implicit information within the message a person transmits. Sarcasm might be used for different purposes, such as criticism or mockery. However, it is hard even for humans to recognize. Therefore, recognizing sarcastic statements can be very useful to improve automatic sentiment analysis of data collected from microblogging websites or social networks. Sentiment Analysis refers to the identification and aggregation of attitudes and opinions expressed by Internet users toward a specific topic. In this paper, we propose a pattern-based approach to detect sarcasm on Twitter. We propose four sets of features that cover the different types of sarcasm we defined. We use those to classify tweets as sarcastic and non-sarcastic. Our proposed approach reaches an accuracy of 83.1% with a precision equal to 91.1%. We also study the importance of each of the proposed sets of features and evaluate its added value to the classification. In particular, we emphasize the importance of pattern-based features for the detection of sarcastic statements.

AB - Sarcasm is a sophisticated form of irony widely used in social networks and microblogging websites. It is usually used to convey implicit information within the message a person transmits. Sarcasm might be used for different purposes, such as criticism or mockery. However, it is hard even for humans to recognize. Therefore, recognizing sarcastic statements can be very useful to improve automatic sentiment analysis of data collected from microblogging websites or social networks. Sentiment Analysis refers to the identification and aggregation of attitudes and opinions expressed by Internet users toward a specific topic. In this paper, we propose a pattern-based approach to detect sarcasm on Twitter. We propose four sets of features that cover the different types of sarcasm we defined. We use those to classify tweets as sarcastic and non-sarcastic. Our proposed approach reaches an accuracy of 83.1% with a precision equal to 91.1%. We also study the importance of each of the proposed sets of features and evaluate its added value to the classification. In particular, we emphasize the importance of pattern-based features for the detection of sarcastic statements.

KW - machine learning

KW - sarcasm detection

KW - sentiment analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84991453560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991453560&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2016.2594194

DO - 10.1109/ACCESS.2016.2594194

M3 - Article

AN - SCOPUS:84991453560

VL - 4

SP - 5477

EP - 5488

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 7549041

ER -