Computational humor recognition: a systematic literature review

Computational humor recognition is considered to be one of the hardest tasks in natural language processing (NLP) since humor is such a particularly complex emotion. There are very few recent studies that offer an analysis of certain aspects of computational humor. However, there has been no attempt to study the empirical evidence on computational humor recognition in a systematic way. The aim of this research is to examine computational humor detection from three aspects: datasets, features and algorithms. Therefore, a Systematic Literature Review (SLR) was carried out to present in detail the computational techniques for humor identification under these aspects. After posing some research questions, a total of 106 primary papers were identified as relevant to the objectives of these questions and further detailed analysis was conducted. The study revealed that there are a great number of publicly available annotated humor datasets with many different types of humor instances. Twenty-one (21) humor features have been carefully studied, and research evidence of their use in humor computational detection is presented. Additionally, a classification of the humor detection approaches was performed, and the results are presented. Finally, the challenges of applying these techniques to humor recognition as well as promising future research directions are discussed.