Paper Info
Title
STARLET: Multi-document Summarization of Service and Product Reviews with Balanced Rating Distributions
Abstract
Reviews about products and services are abundantly available online. However, selecting information relevant to a potential buyer involves a significant amount of time reading user's reviews and weeding out comments unrelated to the important aspects of the reviewed entity. In this work, we present STARLET, a novel approach to multi-document summarization for evaluative text that considers the rating distribution as summarization feature to consistently preserve the overall opinion distribution expressed in the original reviews. We demonstrate how this method improves traditional summarization techniques and leads to more readable summaries.
Year
DOI
Venue
2011
10.1109/ICDMW.2011.158
ICDM Workshops
Keywords
Field
DocType
product reviews,original review,balanced rating distributions,abundantly available online,traditional summarization technique,important aspect,rating distribution,novel approach,multi-document summarization,evaluative text,overall opinion distribution,summarization feature,potential buyer,text analysis,multi document summarization,information retrieval,summarization
Text graph,Data mining,Multi-document summarization,Automatic summarization,Text mining,Information retrieval,Computer science,Product reviews
Conference
Citations 
PageRank 
References 
4
0.74
19
Authors
3
Name
Order
Citations
PageRank
Giuseppe Di Fabbrizio133044.45
Ahmet Aker226730.75
Robert Gaizauskas3923121.46