Document Type

Graduate Project

Date of Degree Completion

Fall 2017

Degree Name

Master of Science (MS)


Computational Science

Committee Chair

Boris Kovalerchuk

Second Committee Member

Razvan Andonie

Third Committee Member

Szilard Vajda


The goal of this project is to investigate the use of visual data mining to model verbal humor. We explored various means of text visualization to identify key featrues of garden path jokes as compared with non jokes. With garden path jokes one interpretation is established in the setup but new information indicating some alternative interpretation triggers some resolution process leading to a new interpretation. For this project we visualize text in three novel ways, assisted by some web mining to build an informal ontology, that allow us to see the differences between garden path jokes and non jokes of similar form. We used the results of the visualizations to build a rule based model which was then compared with models from tradtitional data mining toi show the use of visual data mining. Additional experiments with other forms of incongruity including visualization of ’shilling’ or the introduction of false reviews into a product review set. The results are very similar to that of garden path jokes and start to show us there is a shape to incongruity. Overall this project shows as that the proposed methodologies and tools offer a new approach to testing and generating hypotheses related to theories of humor as well as other phenomena involving opposition, incongruities, and shifts in classification.