Topic Detection and Summarization of User Reviews
This work addresses the problem of extracting useful information from massive, multifaceted customer reviews for users, though it appears incremental as it builds on existing topic modeling and sentiment analysis techniques.
The paper tackles the challenge of generating topic-wise summaries from short, informal customer reviews by proposing a method that analyzes both reviews and summaries, segmenting them into sentiments, applying topic modeling, and using sentiment analysis and a classifier for writing patterns. Experimental results on a new dataset of 1028 products demonstrate the method's effectiveness compared to other approaches.
A massive amount of reviews are generated daily from various platforms. It is impossible for people to read through tons of reviews and to obtain useful information. Automatic summarizing customer reviews thus is important for identifying and extracting the essential information to help users to obtain the gist of the data. However, as customer reviews are typically short, informal, and multifaceted, it is extremely challenging to generate topic-wise summarization.While there are several studies aims to solve this issue, they are heuristic methods that are developed only utilizing customer reviews. Unlike existing method, we propose an effective new summarization method by analyzing both reviews and summaries.To do that, we first segment reviews and summaries into individual sentiments. As the sentiments are typically short, we combine sentiments talking about the same aspect into a single document and apply topic modeling method to identify hidden topics among customer reviews and summaries. Sentiment analysis is employed to distinguish positive and negative opinions among each detected topic. A classifier is also introduced to distinguish the writing pattern of summaries and that of customer reviews. Finally, sentiments are selected to generate the summarization based on their topic relevance, sentiment analysis score and the writing pattern. To test our method, a new dataset comprising product reviews and summaries about 1028 products are collected from Amazon and CNET. Experimental results show the effectiveness of our method compared with other methods.