For the last sev­eral weeks, North­eastern Uni­ver­sity researchers have been using com­pu­ta­tional models to dis­till mas­sive amounts of pres­i­den­tial cam­paign data into nuggets of infor­ma­tion that the human brain can comprehend.

From a “Debate Tweet Meter” to an analysis of super PAC funding, the team has tried to “illu­mi­nate processes by which money is raised and lan­guage is pro­duced,” explained David Lazer, a pro­fessor of polit­ical sci­ence and com­puter and infor­ma­tion sci­ence whose lab is leading the effort. “The machinery around both deeply affects our democracy.”

While Twitter is an obvious go-​​to source for lots of data on voter sen­ti­ment, other sources — such as the RSS feeds of main­stream media sources, the polit­ical “blo­gos­phere” and cam­paign ads — leave traces of the lin­guistic strate­gies intended to sway that sentiment.

To untangle the sources of those strate­gies, Lazer’s inter­dis­ci­pli­nary team of social sci­en­tists, data miners and graphic designers is devel­oping visu­al­iza­tion tools that tell the story behind the lan­guage. Assis­tant research pro­fessor Yu-​​Ru Lin, who leads the Debate Tweet Meter project, sifts through and ana­lyzes large data sets including Tweets or finan­cial con­tri­bu­tions. Assis­tant research pro­fessor Mauro Mar­tino turns those data into dynamic visual rep­re­sen­ta­tions, while post­doc­toral researchers Drew Mar­golin and Sasha Goodman use the infor­ma­tion to make infer­ences about social processes.

The beauty of my lab is that we have these dif­ferent types of people with dif­ferent skills and per­spec­tives,” Lazer said. “And then we shake them up and cool stuff comes out.”

The group is also probing the finan­cial struc­tures behind lan­guage. “A lot of the money sup­ports expen­di­tures on lan­guage,” Lazer said, refer­ring to the spending of polit­ical cam­paigns and polit­ical action committees.

He noted that focus groups and sur­veys, for example, could be used to help cam­paigns tailor their mes­sage to elicit a desired response. From there, the mes­sage per­co­lates through society, leading to “lin­guistic homogeneity.”

Using con­tent from tele­vi­sion com­mer­cials, var­ious types of web­sites and lan­guage used by the can­di­dates them­selves, the researchers are devel­oping what they call the Invis­ible Net­works Project. “We’re looking at the shared chunks of words that are artic­u­lated by politi­cians and the media,” Lazer said. “They are readily iden­ti­fi­able if you look at the data, because it’s exactly the same quotation.”

By iden­ti­fying these texts, the team is con­structing a visual model of the net­work of lan­guage that per­vades our world and influ­ences our everyday experience.

A crit­ical ele­ment of a democ­racy is for people to be exposed to dif­ferent points of view,” Lazer said. “Ulti­mately we’re all sub­ject to the same laws and the same poli­cies.” Lazer’s team is working to reveal those views by laying bare the machinery of money and memes in politics.