Files in this item



application/ (574kB)
Main articlePDF


Title:Was It Worth It? Summarizing and Navigating User Reviews with Natural Language Methods
Author(s):Gilbert, Eric E.
Contributor(s):Karahalios, Karrie
Subject(s):user reviews
social media
Abstract:Popular products often attract an astonishing number of user reviews. Sifting through them by the thousands can be quite a headache, one that has inspired solutions like unique phrase identification (e.g., Yelp) and helpfulness ratings (e.g., Amazon). While clearly useful, these techniques only capitalize on a small subset of the reviews, and cannot an- swer questions like, “do these people care about the same things I care about?” Talking Points is our solution to these problems. It employs natural language methods to summa- rize thousands of user reviews into a navigable, browser- based interface. In addition to describing our novel algo- rithm for feature extraction and sentiment classification, this paper presents the results of an exploratory user study of Talking Points. Our study suggests that users explore reviews far longer with Talking Points than with traditional methods. More surprisingly, in randomized sessions users seemed persuaded to choose those products augmented with Talking Points.
Issue Date:2009-03-31
Citation Info:Submitted to UIST 2009
Genre:Technical Report
Publication Status:published or submitted for publication
Peer Reviewed:is peer reviewed
Sponsor:NSF 0643502
Date Available in IDEALS:2010-06-02

This item appears in the following Collection(s)

Item Statistics