Answers are grounded in this paper and cite their sources.
The increasing volume of scientific publications makes it challenging for researchers to identify relevant literature, detect research opportunities, and prioritize references. This study develops AI-DSS Research Assistant by integrating semantic retrieval, research opportunity analysis, and multi-criteria decision-making methods, namely Simple Additive Weighting (SAW), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and Weighted Product (WP). An initial set of 100 articles was retrieved and screened to obtain an evidence corpus of 20 articles. The system was evaluated using five benchmark queries, relevance judgments, research opportunity analysis, DSS ranking comparisons, and weight sensitivity tests. The results show a Precision@5 of 0.56 (14 of 25 Top-5 results) and a Mean Relevance Score of 3.44 on a 1–5 scale. Two of the 20 articles exhibited research opportunity signals, yielding a signal coverage of 10%. The highest-ranked article under TOPSIS obtained a score of 90.62. Sensitivity testing indicated that weight changes of ±10% and ±20% did not significantly alter the primary TOPSIS recommendation. These findings suggest that the system can support structured literature analysis, while final research gap validation remains the responsibility of the researcher.
No takes yet. Share an insight, caveat, or question.
Aminuddin et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: