Pun Detection using Soft Computing Techniques

Pun is a literary device based on wordplay and ambiguity. It is widely used in many varieties of contemporary and literary texts. The popularity of puns as a feature of humor and Figure of speech makes it imperative for computers to be able to understand and process them. With the advent of social media, the use of puns in funny tweets, posts, blogs, and comments has seen a meteoric rise. In this paper, we intend to explore the task of detecting the presence of pun-based humor in sentences. Soft Computing techniques have shown a great affinity for detection and classification tasks. Hence, we analyze the performance of seven supervised classification algorithms for the task of pun detection on a dataset containing 5000 sample sentences collected from internet sources such as social media websites like Twitter and Facebook. Metrics of accuracy, precision, and recall have been used to evaluate the performance of the classifier.