Researchers at Indiana University’s School of Informatics and Computing designed a system to detect Twitter astroturfing and false memes, and in order to separate the propaganda from fact, they used Stephen Colbert’s truthiness.
Here’s the abstract from the research paper,
Online social media are complementing and in some cases replacing person-to-person social interaction and redefining the diffusion of information. In particular, microblogs have become crucial grounds on which public relations, marketing, and political battles are fought. We introduce an extensible framework that will enable the real-time analysis of meme diffusion in social media by mining, visualizing, mapping, classifying, and modeling massive streams of public microblogging events. We describe a Web service that leverages this framework to track political memes in Twitter and help detect astroturfing, smear campaigns, and other misinformation in the context of U.S. political elections. We present some cases of abusive behaviors uncovered by our service. Finally, we discuss promising preliminary results on the detection of suspicious memes via supervised learning based on features extracted from the topology of the diffusion networks, sentiment analysis, and crowdsourced annotations.
The researchers discussed why astroturfing is different from spam, and more difficult to detect, “While the primary objective of a spammer is often to persuade users to click a link, someone interested in promoting an astroturf message wants to establish a false sense of group consensus about a particular idea. Related to this process is the fact that users are more likely to believe a message that they perceive as coming from several independent sources, or from an acquaintance. Spam detection systems often focus on the content of a potential spam message — for instance, to see if the message contains a certain link or set of tags. In detecting political astroturf, we focus on how the message is delivered rather than on its content.”
They also explained why they borrowed Stephen Colbert’s term truthiness, “In light of these characteristics of political astroturf, we need a definition that allows us to discriminate such falsely-propagated information from organically propagated information that originates at the real grassroots. We thus decided to borrow a term, truthy, to describe political astroturf memes. The term was coined by comedian Stephen Colbert to describe something that a person claims to know based on emotion rather than evidence or facts. We can then define our task as the detection of truthy memes in the Twitter stream.”
The research itself is a fascinating look at how Twitter is manipulated to spread astroturf, smear campaigns, and false political information. They provided a few examples that their model caught of truthy memes spread on Twitter via astroturf,
#ampat The #ampat hashtag is used by many conservative users on Twitter. What makes this meme suspicious is that the bursts of activity are driven by two accounts, @CSteven and @CStevenTucker, which are controlled by the same user, in an apparent effort to give the impression that more people are tweeting about the same topics. This user posts the same tweets using the two accounts and has generated a total of over 41 000 tweets in this fashion. See Figure 7(A) for the diffusion network of this hashtag.
How Chris Coons budget works- uses tax $ 2 attend dinnersand fashion shows.
This is one of a set of truthy memes smearing Chris Coons, the Democratic candidate for U.S. Senate from Delaware. Looking at the injection points of these memes, we uncovered a network of about ten bot accounts. They inject thousands of tweets with links to posts from the freedomist.com Web site. To avoid detection by Twitter and increase visibility to different users, duplicate tweets are disguised by adding different hashtags and appending junk query parameters to the URLs. This works because many URL-shortening services ignore querystrings when processing redirect requests. To generate retweeting cascades, the bots also coordinate mentioning a few popular users. These targets get the appearance of receiving the same news from several different people, and are more likely to think it is true, and spread it to their followers. Most of the bot accounts in this network can be traced back to a single person who runs the freedomist.com Web site. The diffusion network corresponding to this case is illustrated in Figure 7(D).
These are tactics that are used by right wing astroturfers to get their smears and propaganda into the mainstream media. Almost every journalist pays attention to their Twitter account, but what they may not realize is that there are plenty of astroturfers out there who are manipulating Twitter in order to fool mainstream media outlets into giving coverage and credibility to a propagandistic or false message. The research in the paper is from 2010, but the practice of astroturfing Twitter and other forms of social media has only continued to grow.
As America moves towards the 2012 election, you can be certain that the astroturf campaigns against President Obama will kick into high gear. This research serves as a great reminder that the political manipulation of social media isn’t limited to phony candidate Twitter followers and Facebook likes. There is also a covert message war being fought by political operatives on the right every single day across all forms of social media.
The political and cultural impact of Stephen Colbert isn’t limited just to his SuperPAC. Colbert’s concept of truthiness is also helping researchers detect smear campaigns and political astroturfing operations.
Colbert may go down in history as not only the founding father of truthiness, but also the truthiness detector.