Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System

Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System Ankush Khandelwal, Sahil Swami, Syed S. Akthar, Manish Shrivastava Language Technology Research Centre, International Institute of Information Technology, Hyderabad {ankush.k, sahil.swami, syed.akhtar}@research.iiit.ac.in m.shrivastava@iiit.ac.in Abstract The tremendous amount of user generated data through social networking sites led to the gaining popularity of automatic text classification in the field of computational linguistics over the past decade. Within this domain, one problem that has drawn the attention of many researchers is automatic humor detection in texts. In depth semantic understanding of the text is required to detect humor which makes the problem difficult to automate. With increase in the number of social media users, many multilingual speakers often interchange between languages while posting on social media which is called code-mixing. It introduces some challenges in the field of linguistic analysis of social media content (Barman et al., 2014), like spelling variations and non-grammatical structures in a sentence. Past researches include detecting puns in texts (Kao et al., 2016) and humor in one-lines (Mihalcea et al., 2010) in a single language, but with the tremendous amount of code-mixed data available online, there is a need to develop techniques which detects humor in code-mixed tweets. In this paper, we analyze the task of humor detection in texts and describe a freely available corpus containing English-Hindi code-mixed tweets annotated with humorous(H) or non-humorous(N) tags. We also tagged the words in the tweets with Language tags (English/Hindi/Others). Moreover, we describe the experiments carried out on the corpus and provide a baseline classification system which distinguishes between humorous and non-humorous texts. Keywords: humor detection, code-mixing, random forest classifier, SVM, extra tree classifier, naive bayes 1. Introduction “Laughter is the best Medicine” is a saying which is popular with most of the people. Humor is a form of communication that bridges the gap between various languages, cultures, ages and demographics. That’s why humorous content with funny and witty hashtags are so much popular on social media. It is a very powerful tool to connect with the audience. Automatic Humor Recognition is the task of determining whether a text contains some level of humorous content or not. First conference on Computational humor was organized in 1996, since then many research have been done in this field. Kao et al. (2016) does pun detection in one-liners and de Oliveira and Rodrigo (2015) detects humor in Yelp reviews. Because of the complex and interesting aspects involved in detecting humor in texts, it is one of the challenging research field in Natural Language Processing (Attardo, 1994). Identifying humor in a sentence sometimes require a great amount of external knowledge to completely understand it. There are many types of humor, namely anecdotes, fantasy, insult, irony, jokes, quote, self deprecation etc (Hay, 1995; Raz, 2012). Most of the times there are different meanings hidden inside a sentence which is grasped differently by in- dividuals, making the task of humor identification difficult, which is why the development of a generalized algorithm to classify …

Content truncated to 500 words