Money and memes in politics

David Lazer’s interdisciplinary team includes social scientists, graphic designers and data miners. Together they’re using computational modeling to gain insights on society. Photo by Brooks Canaday.

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.