cs.IRAug 2, 2025

When Reviews Are Scarce: Structure-Aware Review Imputation for Recommendation in Realistic Sparse Review Settings

Authors: Leyao Wang, Xutao Mao, Qinwen Ge, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A. Rossi, Nesreen K. Ahmed, 

Organizations: Yale University New Haven, CT, USA · Vanderbilt University Nashville, TN, USA · Adobe Research San Jose, CA, USA · Cisco AI Research Santa Clara, CA, USA

Abstract

Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting in severe sparsity that undermines the effectiveness of review-aware recommenders under partial observability. A natural remedy is to synthesize the missing reviews to restore the textual signal these recommenders rely on. Yet, conventional imputation techniques, such as matrix completion and LLM-based augmentation, either lose contextualized semantics by embedding texts into vectors or overlook structural dependencies on the user-item graph. To address these shortcomings, we propose TWISTER (ToWards Imputation on Sparsity with Textual Edge Graph Representation), a unified framework for sparse-text recommendation that synthesizes missing reviews by jointly modeling semantic and structural signals. Specifically, we represent user-item interactions as a Textual-Edge Graph (TEG), treating reviews as edge attributes. To capture relational context, we construct line-graph views and employ an LLM as a graph-aware aggregator. For each interaction lacking a textual review, our model aggregates natural-language representations from neighboring interactions to generate a coherent and personalized review. Experiments on multiple datasets show that TWISTER consistently outperforms traditional numeric, graph-based, and LLM baselines, delivering higher-quality imputed reviews and, more importantly, improved downstream recommendation. In summary, TWISTER is a drop-in, structure-aware imputer that recovers the textual signal that review-aware recommenders need when reviews are scarce.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation

    Jul 28, 2026He Ma, Chen LiuHeterogeneous GNNsRecommender Systems

  2. How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations

    Jun 15, 2026Eduardo Ferreira da Silva, Mayki dos Santos Oliveira, Joel Machado Pires Denis Dantas Boaventura +1Feature Interaction ModelingRecommender Systems

  3. SISA-Rec: A Semantically Integrated Sequential Recommender with Contrastive Alignment

    Jul 13, 2026Soohan Abbasi, Shahid Munir Shah, Rafia Shaikh +1Sequential RecommendationCold-Start Recommendation