Reproduce “Multicriteria Recommendation System by Leveraging Predefined, Implicit, and Undefined Criteria” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Emrul Hasan, Chen Ding
The authors propose a method that uses review sentences and criteria ratings to predict overall ratings. It matches sentences to predefined criteria by semantic similarity, places below-threshold sentences in an undefined group, and estimates sentiment ratings for both groups. On their TripAdvisor sample, the method achieves MSE 0.3912, versus 0.4220 for MRRRec; this measures prediction error, not recommendation quality.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.