A basic prediction of incongruity theory is that semantic scripts in verbal humor should be in a state of incongruity. We test this prediction using a dataset of 1,182 word/phrase pairs extracted from a set of imperfect puns. Incongruity was defined as the cosine distance between their word vector representations. We compare these pun distances against similarity metrics for the pun words against their synonyms, extracted from WordNet. Results indicate a significantly lower degree of similarity between pun words when compared to their synonyms. Our findings support the basic predictions of incongruity theory and provide computational researchers with a baseline metric to model humorous incongruity.

Prior research undertaken for the purpose of identifying deceptive language has focused on deception as it is used for nefarious ends, such as purposeful lying. However, despite the intent to mislead, not all examples of deception are carried out for malevolent ends. In this study, we describe the linguistic features of humorous deception. Specifically, we analyzed the linguistic features of 753 news stories, 1/3 of which were truthful and 2/3 of which we categorized as examples of humorous deception. The news stories we analyzed occurred naturally as part of a segment named Bluff the Listener on the popular American radio quiz show Wait, Wait...Don’t Tell Me!. Using a combination of supervised learning and predictive modeling, we identified 11 linguistic features accounting for approximately 18% of the variance between humorous deception and truthful news stories. These linguistic features suggested the deceptive news stories were more confident and descriptive but also less cohesive when compared to the truthful new stories. We suggest these findings reflect the dual communicative goal of this unique type of discourse to simultaneously deceive and be humorous.

Using linguistic features to detect figurative language has provided a deeper in-sight into figurative language. The purpose of this study is to assess whether linguistic features can help explain differences in quality of figurative language. In this study a large corpus of metaphors and sarcastic responses are collected from human subjects and rated for figurative language quality based on theoretical components of metaphor, sarcasm, and creativity. Using natural language processing tools, specific linguistic features related to lexical sophistication and semantic cohesion were used to predict the human ratings of figurative language quality. Results demonstrate linguistic features were able to predict small amounts of variance in metaphor and sarcasm production quality.