Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation

TL;DR

This paper introduces TWISTER, a novel framework that models user-item interactions as a Textual-Edge Graph to generate personalized reviews, effectively addressing review sparsity and improving recommendation accuracy.

Contribution

TWISTER uniquely combines semantic and structural signals through a graph-based approach with LLMs to impute missing reviews, advancing beyond traditional methods.

Findings

Outperforms baseline models on Amazon and Goodreads datasets.

Generates more helpful, authentic, and specific reviews.

Enhances recommendation performance through improved review imputation.

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 existing models. A natural solution is to impute or generate missing reviews to enrich the data. However, conventional imputation techniques -- such as matrix completion and LLM-based augmentation -- either lose contextualized semantics by embedding texts into vectors, or overlook structural dependencies among user-item interactions. To address these shortcomings, we propose TWISTER (ToWards Imputation on Sparsity with Textual Edge Graph Representation), a unified framework that imputes 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 a large language model as a graph-aware aggregator. For each interaction lacking a textual review, our model aggregates the neighborhood's natural-language representations to generate a coherent and personalized review. Experiments on the Amazon and Goodreads datasets show that TWISTER consistently outperforms traditional numeric, graph-based, and LLM baselines, delivering higher-quality imputed reviews and, more importantly, enhanced recommendation performance. In summary, TWISTER generates reviews that are more helpful, authentic, and specific, while smoothing structural signals for improved recommendations.