Summarizing Reviews with Variable-length Syntactic Patterns and Topic Models

TL;DR

This paper introduces a novel review summarization method that combines syntactic pattern extraction with sentiment topic modeling to produce more informative and user-rated summaries of product and service reviews.

Contribution

The paper proposes a new framework that integrates variable-length syntactic pattern extraction with a joint sentiment topic model for improved review summarization.

Findings

Outperforms previous methods in extracting informative segments

Produces summaries that better capture product and service aspects

User study shows higher usefulness ratings for the summaries

Abstract

We present a novel summarization framework for reviews of products and services by selecting informative and concise text segments from the reviews. Our method consists of two major steps. First, we identify five frequently occurring variable-length syntactic patterns and use them to extract candidate segments. Then we use the output of a joint generative sentiment topic model to filter out the non-informative segments. We verify the proposed method with quantitative and qualitative experiments. In a quantitative study, our approach outperforms previous methods in producing informative segments and summaries that capture aspects of products and services as expressed in the user-generated pros and cons lists. Our user study with ninety users resonates with this result: individual segments extracted and filtered by our method are rated as more useful by users compared to previous approaches by users.