Advertisement

An Improved Approach for Sarcasm Detection Avoiding Null Tweets

  • Santosh Kumar BhartiEmail author
  • Korra Sathya Babu
  • Sambit Kumar Mishra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11942)

Abstract

Among the plethora of social media, Twitter has emerged as the favorite destination for researchers in recent times. Many researchers are inclined to work on Twitter due to the availability of massive tweets and its unique features like hashtags and short messages. In recent times, various studies have preferred the hashtags (#sarcasm and #sarcastic) to collect Twitter dataset for sarcasm detection. However, hashtag-based distant supervision suffers from the problem of the inclusion of null tweets in the datasets which can be considered as a critical one for sarcasm detection. In this article, an algorithm is proposed for automatic detection and filtration of null tweets in the Twitter data. Additionally, an algorithm to identify sarcastic tweets using context within a tweet is also proposed. This approach use dictionaries of handpicked hashtag words, emoticons as the context within a tweet. Finally, we deployed a rule-based algorithm to analyse the performance of the proposed approach. The proposed approach attains the accuracy of 97.3% (after filtering null tweets) and 83.13% (without filtering null tweets) using a rule-based approach. The attained results conclude that after elimination of null tweets, the performance of the proposed system improved significantly.

Keywords

Context-based Emoticons Hashtag word Negation word Null tweets Social media Sarcastic Sentiment 

References

  1. 1.
    Bamman, D., Smith, N.A.: Contextualized sarcasm detection on twitter. In: Ninth International AAAI Conference on Web and Social Media (2015)Google Scholar
  2. 2.
    BBC: Us secret service seeks twitter sarcasm detector. http://www.bbc.com/news/technology-27711109/ (2014)
  3. 3.
    Bharti, S.K., Babu, K.S.: Sarcasm as a contradiction between a tweet and its temporal facts: a pattern-based approach. Int. J. Nat. Lang. Comput. (IJNLC) 7, 67–79 (2018)CrossRefGoogle Scholar
  4. 4.
    Bharti, S.K., Sathya Babu, K., Jena, S.K.: Harnessing online news for sarcasm detection in Hindi Tweets. In: Shankar, B.U., Ghosh, K., Mandal, D.P., Ray, S.S., Zhang, D., Pal, S.K. (eds.) PReMI 2017. LNCS, vol. 10597, pp. 679–686. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-69900-4_86CrossRefGoogle Scholar
  5. 5.
    Bharti, S.K., Babu, K.S., Raman, R.: Context-based sarcasm detection in Hindi Tweets. In: 2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), pp. 1–6. IEEE (2017)Google Scholar
  6. 6.
    Bharti, S., Vachha, B., Pradhan, R., Babu, K., Jena, S.: Sarcastic sentiment detection in tweets streamed in real time: a big data approach. Digit. Commun. Netw. 2(3), 108–121 (2016)CrossRefGoogle Scholar
  7. 7.
    Davidov, D., Tsur, O., Rappoport, A.: Semi-supervised recognition of sarcastic sentences in Twitter and Amazon. In: Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pp. 107–116. Association for Computational Linguistics (2010)Google Scholar
  8. 8.
    Joshi, A., Sharma, V., Bhattacharyya, P.: Harnessing context incongruity for sarcasm detection. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, vol. 2, pp. 757–762 (2015)Google Scholar
  9. 9.
    Khattri, A., Joshi, A., Bhattacharyya, P., Carman, M.J.: Your sentiment precedes you: using an author’s historical tweets to predict sarcasm. In: 6th Workshop on Computation Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA) 2015, p. 25 (2015)Google Scholar
  10. 10.
    Maynard, D., Greenwood, M.A.: Who cares about sarcastic tweets? Investigating the impact of sarcasm on sentiment analysis. In: LREC 2014 Proceedings. ELRA (2014)Google Scholar
  11. 11.
    Schifanella, R., de Juan, P., Tetreault, J., Cao, L.: Detecting sarcasm in multimodal social platforms. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 1136–1145. ACM (2016)Google Scholar
  12. 12.
    Tungthamthiti, P., Kiyoaki, S., Mohd, M.: Recognition of sarcasms in tweets based on concept level sentiment analysis and supervised learning approaches. In: Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing, pp. 404–413 (2014)Google Scholar
  13. 13.
    Wang, Z., Wu, Z., Wang, R., Ren, Y.: Twitter sarcasm detection exploiting a context-based model. In: Wang, J., et al. (eds.) WISE 2015. LNCS, vol. 9418, pp. 77–91. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-26190-4_6CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Pandit Deendayal Petroleum UniversityGandhinagarIndia
  2. 2.National Institute of TechnologyRourkelaIndia
  3. 3.ITER, SOA UniversityBhubaneswarIndia

Personalised recommendations