Digital assemblages with AI for creative interpretation of short stories

TY - JOUR

T1 - Digital assemblages with AI for creative interpretation of short stories

AU - O'Halloran, Kieran

N1 - Publisher Copyright: © The Author(s) 2024.

PY - 2024/6/18

Y1 - 2024/6/18

N2 - I demonstrate an approach fostering inventive interpretation of short stories in Literary Studies and higher education generally. It involves constructing an ‘assemblage’—at its simplest, an evolving network of unusual connections for creative outcome. The assemblage of this article combines freshly located research literature, directly and indirectly related to a story’s themes, and/or the personality type of protagonists. Importantly, this assemblage also utilizes text analysis software revealing the relatively invisible (e.g. (in)frequent words, parts of speech, and topics) and Large Language Model (LLM) Generative AI to enrich the interpretation. The use of all these elements helps productively exceed initial intuitions about the story, facilitating creativity. I model the approach using Edgar Allan Poe’s short story, The Black Cat, whose protagonist is a homicidal psychopath. Specifically, the assemblage here includes relevant software-based research (a corpus analysis of homicidal psychopathic language), non-software-based research (psychoanalytical literary criticism of The Black Cat using the empirically validated concept of transference), text analysis software (WMatrix and Datayze), and the LLM Generative AI, ‘ChatGPT’ (using the freely available LLM GPT-3.5). One use of this approach is as a pedagogy in Literary Studies employing text analysis software (e.g. on a digital stylistics course). Yet given creative adaptability is a key 21st-century skill, with digital literacy—including the use of Generative AI—an important contemporary competence, and with the short story genre universally known, I highlight too the utility of this approach as a university-wide pedagogy for enhancing creative thinking.

AB - I demonstrate an approach fostering inventive interpretation of short stories in Literary Studies and higher education generally. It involves constructing an ‘assemblage’—at its simplest, an evolving network of unusual connections for creative outcome. The assemblage of this article combines freshly located research literature, directly and indirectly related to a story’s themes, and/or the personality type of protagonists. Importantly, this assemblage also utilizes text analysis software revealing the relatively invisible (e.g. (in)frequent words, parts of speech, and topics) and Large Language Model (LLM) Generative AI to enrich the interpretation. The use of all these elements helps productively exceed initial intuitions about the story, facilitating creativity. I model the approach using Edgar Allan Poe’s short story, The Black Cat, whose protagonist is a homicidal psychopath. Specifically, the assemblage here includes relevant software-based research (a corpus analysis of homicidal psychopathic language), non-software-based research (psychoanalytical literary criticism of The Black Cat using the empirically validated concept of transference), text analysis software (WMatrix and Datayze), and the LLM Generative AI, ‘ChatGPT’ (using the freely available LLM GPT-3.5). One use of this approach is as a pedagogy in Literary Studies employing text analysis software (e.g. on a digital stylistics course). Yet given creative adaptability is a key 21st-century skill, with digital literacy—including the use of Generative AI—an important contemporary competence, and with the short story genre universally known, I highlight too the utility of this approach as a university-wide pedagogy for enhancing creative thinking.

KW - AI literacy; assemblage; corpus stylistics; creative interpretation of literature; diffractive reading; digital stylistics; distant reading; distant-diffractive reading; Edgar Allan Poe (‘The Black Cat’); Large Language Model Generative AI; literary studi

UR - http://www.scopus.com/inward/record.url?scp=85196492721&partnerID=8YFLogxK

U2 - 10.1093/llc/fqad050

DO - 10.1093/llc/fqad050

M3 - Article

SN - 2055-7671

VL - 39

SP - 657

EP - 689

JO - Digital Scholarship in the Humanities

JF - Digital Scholarship in the Humanities

IS - 2

ER -