Prioritizing Generative Artificial Intelligence Co-Writing Tools in Newsrooms: A Hybrid MCDM Framework for Transparency, Stability, and Editorial Integrity

Fenglan Chen (), Bella Akhmedovna Bulgarova and Raman Kumar
Additional contact information
Fenglan Chen: Department of Mass Communications, Peoples’ Friendship University of Russia Named After Patrice Lumumba (RUDN University), Miklukho-Maklaya Str. 6, 117198 Moscow, Russia
Bella Akhmedovna Bulgarova: Department of Mass Communications, Peoples’ Friendship University of Russia Named After Patrice Lumumba (RUDN University), Miklukho-Maklaya Str. 6, 117198 Moscow, Russia
Raman Kumar: Department of Mechanical and Production Engineering, Guru Nanak Dev Engineering College, Ludhiana 141006, India

Mathematics, 2025, vol. 13, issue 23, 1-28

Abstract: The rapid integration of generative artificial intelligence (AI) into newsroom workflows has transformed journalistic writing. Still, selecting reliable co-writing tools remains a multi-criteria challenge as it involves technical, ethical, and economic trade-offs. This study develops a hybrid multi-criteria decision-making (MCDM) framework that integrates the Measurement of Alternatives and Ranking according to the Compromise Solution (MARCOS) model with Entropy, CRITIC, MEREC, CILOS, and Standard Deviation objective weighting methods fused through the Bonferroni operator to reduce subjectivity and enhance robustness. Nine generative AI tools, including ChatGPT, Claude, Gemini, and Copilot, were evaluated against sixteen benefit- and cost-type criteria encompassing accuracy, usability, transparency, risk, and scalability. The decision matrix was normalized and benchmarked against ideal and anti-ideal profiles. The MCDM model was validated through correlation and sensitivity analyses using Spearman’s and Kendall’s coefficients. The results indicate that Gemini and Claude achieved the highest overall performance due to superior factual accuracy, transparency, and workflow integration, while ChatGPT demonstrated high linguistic versatility. The hybrid model achieved a stability index above 0.9 across perturbation scenarios, confirming its consistency and reliability. Overall, the proposed MARCOS–objective weight framework provides a mathematically transparent and reproducible decision protocol for newsroom technology evaluation, supporting evidence-based selection of generative AI co-writing systems.

Keywords: MARCOS; entropy weighting; CRITIC method; Bonferroni operator; multi-criteria decision-making (MCDM); generative AI; co-writing tools; newsroom technology evaluation; decision matrix optimization (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/23/3791/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/23/3791/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:23:p:3791-:d:1803286

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().