Printer Friendly

Indiana University scientists get truthy.

A group of Indiana University (IU) computer and information scientists released Truthy, a Twitter-based research tool that brings together such elements as data mining and crowd sourcing in order to reveal intentional misinformation and smearing tactics in the lead-up to the Nov. 2 elections. The team behind Truthy plans to use the tool to isolate patterns of interest and to obtain more information about a particular meme's history.

Users are free to visit Truthy to view diffusion network images that identify retweets, mentions, and the full extent and life cycle of the trend in question. Users can also view the output of a sentiment analysis algorithm, which identifies mood-specific words and assesses them on a psychometric scale. The meme is then classified according to mood scales ranging from anxious to calm, kind to hostile, sure to unsure, and aware to confused.

The idea for Truthy was conceived partially in response to the Twitter bomb campaign organized by American Future Fund (AFF), a conservative group, against Martha Coakley, a Democrat who was running for the senatorial seat once held by Edward Kennedy. Coakley's opponent, Republican Scott Brown, bested her in the race, but not before AFF set up nine Twitter accounts and sent out 929 tweets attacking Coakley in the hours leading up to the election. The slanderous tweets reached at least 60,000 people before Twitter recognized them as spam.

Truthy is being headed by several personnel at IU hoping to help avoid a similar scenario during the Nov. 2 elections. These people include Filippo Menczer, the associate director of IU's Center for Complex Networks and Systems Research; Alessandro Vespignani, professor of informatics; Alessandro Flammini, associate professor of informatics; and Johan Bollen, associate professor of informatics and computing.

COPYRIGHT 2010 Information Today, Inc.
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2010 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Title Annotation:news desk
Author:Stewart, Bill
Publication:Computers in Libraries
Article Type:Brief article
Geographic Code:1USA
Date:Nov 1, 2010
Words:288
Previous Article:Location, location, location: making foursquare work for your library.
Next Article:ProQuest releases new National Security Archive collection.
Topics:

Terms of use | Privacy policy | Copyright © 2019 Farlex, Inc. | Feedback | For webmasters