Abstract After the GPT-3 boom, there is an ongoing debate regarding the language heuristics in automatic text generation, as well as their usefulness for scientific inquiry. In this article, we conduct a computational study that engages in a discursive problematization of textual analysis methods, seeking to reconcile epistemological tensions between positivist and interpretive paradigms in Psychology, Literature, and Computer Science. For our “experiment”, (a) a pseudo-random probabilistic language model is trained on a classical narrative works containing epic and heroic traits; (b) a stochastic text is generated using n-gram modeling in Python; (c) the output text is interpreted using Analytical Psychology and Literary Criticism; (d) an integrative discussion reconciles the previous steps, suggesting a new methodological approach for ideation and theorizing in scientific endeavors. We conclude the study optimistically, highlighting the benefits of this mode of inquiry for social psychology.
ARCHETYPAL ANALYSIS OF STOCHASTIC TEXTS: A DIALOGICAL HUMAN-ALGORITHMIC APPROACH
G. M. Ferratti,Sérgio Ricardo Perassoli Jr.,Silvio Eduardo Alvarez Cândido,Mario Sacomano Neto,Aparecido Donizete Rossi
Published 2025 in Psicologia & Sociedade
ABSTRACT
PUBLICATION RECORD
- Publication year
2025
- Venue
Psicologia & Sociedade
- Publication date
Unknown publication date
- Fields of study
Not labeled
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-30 of 30 references · Page 1 of 1
CITED BY
- No citing papers are available for this paper.
Showing 0-0 of 0 citing papers · Page 1 of 1