Communications of the ACM
Computer Science Team Wins Challenge to Improve Reading Process of Reviews
Credit: Free Stock Photos
Virginia Tech researchers say they have developed a better method of summarizing text through the mining or retrieval of key data, which won a Yelp-sponsored contest. The goal was to help guess an online review's rating from its text alone.
The researchers developed software that enabled them to cluster specific types of words to summarize the product reviews, and infer relations from the text that would guide users to more insight and pertinent information. The researchers also were able to embed the semantic information of a grammatical dependency graph into a word cloud. "Our specific word cloud is designed to provide more insight about user-generated reviews by creating clusters based on semantic information," says Virginia Tech researcher Ji Wang.
Wang says that word clouds are very popular text visualization tools. "They provide the frequency data of a variety of text sources and encode the frequency into the word's font size," he says. "The clustered layout cloud we developed embeds semantic information to the clustered layout to present the review content."
The researchers hope to add more interactions to the technique, which would enable user to modify the natural language processing results, visualization results, and raw data by interaction to obtain customized visual analytics.
From Virginia Tech
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found