Trivdedi, Anshul, Çetinkaya, Yusuf Mucahit, Cowan, Michael A., Newson, Martha ORCID: https://orcid.org/0000-0001-7700-9562, Vlahović, Natko and Davuclu, Hasan (2026) Beyond the Black Box: programmable AI and explainable text analysis for trustworthy social intelligence. IEEE Transactions on Computational Social Systems. ISSN 2329-924X (Online) (In Press)

Preview

PDF (Author's Accepted Manuscript) 52868 NEWSON_Beyond_The_Black_Box_Programmable_AI_And_Explainable_Text_Analysis_(AAM)_2026.pdf - Accepted Version Available under License Creative Commons Attribution. Download (7MB) | Preview

Abstract

Life demands safe, reliable, and explainable AI grounded in scientific reasoning and guided by human oversight. We present a neuro-symbolic Programmable AI algorithm that transforms neural outputs into interpretable logic-patterned narratives via symbolic pattern lifting and lowering. It is designed for social scientists and enables reproducible Human + AI text analysis across sources like social media, interviews, and news. It is demonstrated on 1.3 million tweets about global energy trends, and the system ensures AI that not only says what it does but does what it says, replacing black-box opacity with transparent, accountable reasoning.

Item Type:	Article
Uncontrolled Keywords:	programmable AI, explainable AI, symbolic patterning, AI interpretability, Human-AI collaboration
Subjects:	B Philosophy. Psychology. Religion > BF Psychology H Social Sciences > H Social Sciences (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Education, Health & Human Sciences Faculty of Education, Health & Human Sciences > Institute for Lifecourse Development Faculty of Education, Health & Human Sciences > Institute for Lifecourse Development > Centre for Inequalities Faculty of Education, Health & Human Sciences > School of Human Sciences (HUM)
Last Modified:	24 Apr 2026 16:01
URI:	https://gala.gre.ac.uk/id/eprint/52868

Actions (login required)

View Item

Downloads