EUVIMEDEUVIMED entdecken
Crossref

A Human-Centered Computational Intelligence Framework for AI-Assisted Reasoning, Digital Analytics, and Decision-Making in Social Sciences and Literature

Dr. Ruchi Mishra, Dr. Pooja Bali, Dr. Srilakshmi Kovvali, Dr. Vikas Gajananrao Bhowate, Dipankar Boruah, Dr. Antony George

Computer and Decision Making An International Journal · 04.11.2026

DOI: 10.1922/comdem.v3i6s.19164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 04.11.2026. Verfasst von Dr. Ruchi Mishra und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human-centered computational intelligence provides a structured approach for bridging the gap between human reasoning and artificial intelligence in analytical and decision-making processes within a text-based context. A cross domain comparative framework has been developed to explore the relationship between literary/readability and argumentative-writing evidence and its analysis, human-referenced scoring, explainability, and decision-support interpretation. The framework included verified characteristics from the corpus, output of models reported for the text collections to which the corpus belongs, and differences in task design and evaluation measures. Readability modelling based on 28 linguistic predictors yielded RMSE = 0.726, MAE = 0.575, r = 0.712, and R² = 0.507. In terms of scoring 13,121 independent essays, zero-shot GPT-4o achieved a score of QWK = 0.437 (95% CI: 0.387–0.487), unweighted kappa = 0.082, and PRMSE = -0.617, while the expert human ratings for the underlying corpus achieved weighted kappa = 0.745 and r = 0.750. The contrast revealed that the computational support in structured readability prediction was more reliable than holistically reading an essay without any support. Explainability and human oversight were thus the cornerstones of the framework, which took the form of an easily transferable foundation for responsible AI-supported reasoning and decision-making processes for argumentative analysis in the social sciences as well as for literary text analytics.

Zitieren

APA

Mishra, D. R., Bali, D. P., Kovvali, D. S., Bhowate, D. V. G., Boruah, D., & George, D. A. (2026). A Human-Centered Computational Intelligence Framework for AI-Assisted Reasoning, Digital Analytics, and Decision-Making in Social Sciences and Literature. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v3i6s.19164

Vancouver

Mishra DR, Bali DP, Kovvali DS, Bhowate DVG, Boruah D, George DA. A Human-Centered Computational Intelligence Framework for AI-Assisted Reasoning, Digital Analytics, and Decision-Making in Social Sciences and Literature. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v3i6s.19164

BibTeX
@article{Mishra2026,
  author = {Mishra, Dr. Ruchi and Bali, Dr. Pooja and Kovvali, Dr. Srilakshmi and Bhowate, Dr. Vikas Gajananrao and Boruah, Dipankar and George, Dr. Antony},
  title = {A Human-Centered Computational Intelligence Framework for AI-Assisted Reasoning, Digital Analytics, and Decision-Making in Social Sciences and Literature},
  journal = {Computer and Decision Making An International Journal},
  year = {2026},
  doi = {10.1922/comdem.v3i6s.19164}
}
Kostenlos starten →