In the field of humor research, there has been a recent surge of interest in the sub-domain of Conversational Humor (CH). This study has two main objectives. (a) develop a conversational (humorous and non-humorous) dataset in Telugu. (b) detect CH in the compiled dataset. In this paper, the challenges faced while collecting the data and experiments carried out are elucidated. Transfer learning and non-transfer learning techniques are implemented by utilizing pre-trained models such as FastText word embeddings, BERT language models and Text GCN, which learns the word and document embeddings simultaneously of the corpus given. State-of-the-art results are observed with a 99.3% accuracy and a 98.5% f1 score achieved by BERT.

Humor research is a multifaceted field that has led to a better understanding of humor’s psychological effects and the development of different theories of humor. This paper’s main objective is to develop a hierarchical schema for a fine-grained annotation of Conversational Humor. Based on the Benign Violation Theory, the benignity or non-benignity of the interlocutor’s intentions is included within the framework. Under the categories mentioned above, in addition to different types of humor, the techniques utilized by these types are identified. Furthermore, a prominent play from Telugu, Kanyasulkam, is annotated to substantiate the work across cultures at multiple levels. The inter-annotator agreement is calculated to assess the accuracy and validity of the dataset. An in-depth analysis of the disagreement is performed to understand the subjectivity of humor better.