Analytics tool helps voters search social media streams of Obama, Romney campaigns

Computerworld - Data analytics firm Atigeo has released an online tool designed to help voters quickly research the positions of the two major U.S. presidential candidates on a wide range of election issues.

The tool uses a contextual semantic search technology to let users pull data from the social media feeds of both President Barack Obama and GOP challenger Mitt Romney, and their respective parties' Twitter, RSS feeds and Facebook pages.

The tool (available at Red2012Blue.com and Blue2012Red.com) lets voters use simple search terms to pull up every Tweet, Facebook post and blog item that either candidate or their respective parties have posted on the issue.

All of the search results are organized by party. Users can click on each result to see the raw material and drag each search result to a 'relation box' in the center of the screen to get an immediate view of all related content from both sides. All results are organized and presented to the user based on relevance to the original query.

An embedded data visualization tool lets users view the search results for a particular query in 3D format. Users can rotate the image, zoom in on specific results and move it around to see if they can find any non-obvious or unforeseen relationships in the results.

The goal is to "present the content being shared by the candidates and their parties via social networks in a completely agnostic manner" and in their original raw format, said Christopher Burgess, chief operating officer and chief security officer of Atigeo. The tool currently tracks 12 data feeds across both parties.

Burgess did not say how many tweets or others posts are being generated each day, but noted that Democrats have been out-producing Republicans by a 3-to-1 margin in terms of the overall number of posts being tracked.

A quick Computerworld review of the tool shows that users can indeed pull in a lot of data from both parties' social media posts. However, not all of the results appeared to be relevant to the query. Searching for posts related to "cybersecurity," for instance, generated links to tweets and posts on economic security, job security and physical security. The tool does not allow users to sort or filter results, as Atigeo's commercial implementations allow.

Atigeo's tool is powered by the company's xPatterns semantic search platform. The technology is designed to let organizations search vast sets of structured and unstructured data for hidden correlations and connections. According to Burgess, the technology can be used to process large volumes of data to glean actionable business intelligence from seemingly disconnected bits of information.

The company has partned with several organizations to demonstrate real-use cases for its technology, Burgess said. One example is Atigeo's xPatterns Explorer for PubMed. The tool is designed to enable better medical research by letting users quickly search through and correlate information from the more 400,000 documents stored within the U.S. National Institutes of Health's PubMed body of medical research.

The company's xPatterns Domain Explorer for Wikipedia enables a similar search of all the content on Wikipedia's domain, Burgess said.

Jaikumar Vijayan covers data security and privacy issues, financial services security and e-voting for Computerworld. Follow Jaikumar on Twitter at @jaivijayan or subscribe to Jaikumar's RSS feed . His e-mail address is jvijayan@computerworld.com.

See more by Jaikumar Vijayan on Computerworld.com.

Read more about Business Intelligence/Analytics in Computerworld's Business Intelligence/Analytics Topic Center.