Abstract
This paper examines the ways IBM Statistical Package for the Social Sciences (SPSS) Modeler and Watson Studio can be used to uncover the hidden structures behind literary texts, and open up new levels of interpretation. In particular, I will look at how they can decipher the plays of Bernard Shaw and reveal hidden intentions of the playwright. Shaw’s plays are meant more to be read than performed. Not only are there detailed stage directions, long prefaces and dialogues have much exacerbated the reading process. The readers or audience have the daunting tasks to plough through the lengthy texts to uncover meanings and discern word patterns. These are complicated by the volumes of non-dramatic writings written alongside the plays, in response to contemporary topical issues. Taken together, this is the sort of big data suitable for text mining by the artificial intelligence functionalities on IBM Cloud. Through analysis by IBM Statistical Package for the Social Sciences (SPSS) Modeler and Watson Studio, I will show how the textual and contextual materials have underlying patterns of interrelated concepts and categories that open up new levels of interpretation. These patterns have heretofore escaped attention as the corpus is too large for analysis by the human mind. A trained textual modeler powered by machine learning can conduct meaningful literary analysis. Artificial intelligence can be an invaluable asset to the arts, with the machine learning designed and modelled by literary experts.
Details
Presentation Type
Theme
2021 Special Focus: Critical Thinking, Soft Skills, and Technology
KEYWORDS
LITERATURE, ARTIFICIAL INTELLIGENCE, BERNARD SHAW, LITERARY CRITICISM