CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews

--Consumers often heavily rely on online product reviews, analyzing both quantitative ratings and textual descriptions to assess product quality. However, existing research hasn't adequately addressed how to systematically encourage the creation of comprehensive reviews that capture both customers sentiment and detailed product feature analysis. This paper presents CPR, a novel methodology that leverages the power of Large Language Models (LLMs) and T opic Modeling to guide users in crafting insightful and well-rounded reviews. Our approach employs a three-stage process: first, we present users with product-specific terms for rating; second, we generate targeted phrase suggestions based on these ratings; and third, we integrate user-written text through topic modeling, ensuring all key aspects are addressed. We evaluate CPR using text-to-text LLMs, comparing its performance against real-world customer reviews from Walmart. Our results demonstrate that CPR effectively identifies relevant product terms, even for new products lacking prior reviews, and provides sentiment-aligned phrase suggestions, saving users time and enhancing reviews quality. Quantitative analysis reveals a 12.3% improvement in BLEU score over baseline methods, further supported by manual evaluation of generated phrases. We conclude by discussing potential extensions and future research directions. I NTRODUCTION Product reviews play a crucial role for retailers, as they help build trust among potential customers by providing social proof. They influence purchase decisions [7], [9], [19], [25] by offering information on the quality and suitability of the product. Reviews also provide valuable feedback for retailers, allows them to improve their products and enhance customer satisfaction. Furthermore, product reviews contribute to product search optimization efforts [8], giving retailers a competitive advantage and fostering customer engagement and loyalty. Product review phrase suggestion is a sub-task of text-to-text generation in natural language processing (NLP). Online shopping is increasingly popular. However, customers often lack the motivation to write constructive reviews.