Tag Archives: Twitter

Truthy Team Wins WICI Data Challenge

WICI Data Challenge AwardCongratulations to Przemyslaw Grabowicz, Luca Aiello, and Fil Menczer for winning the WICI Data Challenge. A prize of $10,000 CAD accompanies this award from the Waterloo Institute for Complexity and Innovation at the University of Waterloo. The Challenge called for tools and methods that improve the exploration, analysis, and visualization of complex-systems data. The winning entry, titled Fast visualization of relevant portions of large dynamic networks, is an algorithm that selects subsets of nodes and edges that best represent an evolving graph and visualizes it either by creating a movie, or by streaming it to an interactive network visualization tool. The algorithm is deployed in the movie generation tool of the Truthy system, which allows users to create, in near-real time, YouTube videos that illustrate the spread and co-occurrence of memes on Twitter. Przemek and Luca worked on this project while visiting CNetS in 2011 and collaborating with the Truthy team. Bravo!

Postdoctoral Researcher in Analysis and Modeling of Social Networks

Network of Political Retweets

[UPDATE: this position has been filled.]

The Center for Complex Networks and Systems Research has an open postdoctoral position to study how ideas propagate through complex online social networks. The position is funded by a McDonnell Foundation’s grant in Complex Systems. The appointment starts as early as possible after January 2013 for one year and is renewable for up to 2 additional years. The salary is competitive and benefits are generous.

The postdoc will join a dynamic and interdisciplinary team that includes computer, physical, and cognitive scientists. The postdoc will work with PIs Filippo Menczer and Alessandro Flammini, other postdocs, and several PhD students on analysis and modeling of social media data. Areas of focus will include information diffusion patterns, epidemic models for the spread of ideas, interactions between network traffic and structure dynamics, and agent-based models to explain the emergence of viral bursts of attention. Domains of study will include politics, scientific knowledge, and world events. Go to the grant page or project page for further details on the team and project.

The ideal candidate will have a PhD in computing or physical sciences; a strong background in analysis and modeling of complex systems and networks; and solid programming skills necessary to handle big data and develop large scale simulations.

To apply, email/send a CV and names and emails of three references to Tara Holbrook. Applications received by 15 December 2012 will receive full consideration, but applications will be considered until the position is filled.

Indiana University is an Equal Opportunity/Affirmative Action employer. Applications from women and minorities are strongly encouraged. IU Bloomington is vitally interested in the needs of Dual Career couples.

Thanks to KDnuggets, SOCNET, Gephi, DBWorld, Air-L, CITASA and others for help in advertising this position.

PLEAD 2012 keynote

PLEAD 2012I was honored to give a keynote presentation at PLEAD 2012, the CIKM Workshop on Politics, Elections and Data. My talk was titled The diffusion of political memes in social media. The workshop was held in beautiful Maui Hawaii, but alas, I could not attend in person and gave the presentation remotely via skype 🙁

IARPA contract to study new ways to forecast critical societal events

University and industry scientists are determining how to forecast significant societal events, ranging from violent protests to nationwide credit-rate crashes, by analyzing the billions of pieces of information in the ocean of public communications, such as tweets, web queries, oil prices, and daily stock market activity.

“We are automating the generation of alerts, so that intelligence analysts can focus on interpreting the discoveries rather than on the mechanics of integrating information,” said Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering in the computer science department at Virginia Tech. He is leading the team of computer scientists and subject-matter experts from Virginia Tech, the University of Maryland, Cornell University, Children’s Hospital of Boston, San Diego State University, University of California at San Diego, and Indiana University, and from the companies, CACI International Inc., and Basis Technology.

CNetS Professors Bollen and Rocha from the School of Informatics and Computing at Indiana University are members of this project. Prof. Bollen, has devised a way to evaluate the tone of tweets – calm, alert, vital, etc. — to predict stock market trends. Prof. Rocha, has developed bio-inspired methods to predict associations in biochemical, social, and knowledge networks, including web and e-mail systems.

Additional details: Researchers study new ways to forecast critical societal events.

DARPA award

Prof. Flammini (PI) and Menczer have been awarded a three-year, $2M grant from DARPA in the context of the Social Media in Strategic Communication (SMISC) program, whose primary goal is “to develop a new science of social networks built on an emerging technology base,” Our IU unit leads a three-group team that includes collaborators at Lockheed-Martin Advanced Technology Lab and the University of Michigan. The funded project is aimed at designing and implementing a system to detect online persuasion campaigns.

2011 Truthy Updates

WSJ video on Truthy project
Mike Conover in the WSJ's report on the Truthy project

We’re pleased to report several exciting developments in our interdisciplinary project studying information diffusion in complex online social networks. The past year has resulted in several publications. Our results on the Truthy astroturf monitoring and detection system were presented at WWW 2011 and ICWSM 2011. Research into the polarized network structure of political communication on Twitter was presented at ICWSM and received the 2011 CITASA Best Student Paper Honorable Mention. We demonstrated the feasibility of the prediction of individuals’ political affiliation from network and text data (SocialCom 2011), a machine learning application that enables large-scale instrumentation of nearly 20,000 individuals’ political behaviors, policy foci, and geospatial distribution (Journal of Information Technology and Politics). We’re also working on a paper on partisan asymmetries in online political activity surrounding the 2010 U.S. congressional midterm elections.

Our results have been widely covered in the press, including the Wall Street JournalScienceCommunications of the ACM, NPR [1,2], The Chronicle of Higher Education, Discover Magazine, The Atlantic, New ScientistMIT Technology Review, and many more.

Current and future research is supported by an award from the NSF Interface between Computer Science and Economics & Social Sciences program, and a McDonnell Foundation grant. The former will focus on building an infrastructure for the study of information diffusion in social media, the characterization of meme spread patterns, and the development of sentiment analysis tools for social media. The latter will focus on modeling efforts, especially agent-based models of information diffusion, competition for attention, and the relationship between information sharing events and social network evolution.

Postdoctoral Researcher in Analysis and Modeling of Social Networks

Network of Political Retweets

The Center for Complex Networks and Systems Research has an open postdoctoral position to study how ideas propagate through complex online social networks. The position is funded by a McDonnell Foundation’s grant in Complex Systems. The appointment starts in January 2012 for one year and is renewable for up to 3 additional years. The salary is competitive and benefits are generous.

The postdoc will join a dynamic and interdisciplinary team that includes computer, physical, and cognitive scientists. The postdoc will work with PIs Filippo Menczer and Alessandro Flammini and several PhD students on analysis and modeling of social media data. Areas of focus will include information diffusion patterns, epidemic models for the spread of ideas, interactions between network traffic and structure dynamics, and agent-based models to explain the emergence of viral bursts of attention. Domains of study will include politics, scientific knowledge, and world events. Go to the grant page or project page for further details on the team and project.

The ideal candidate will have a PhD in computing or physical sciences; a strong background in analysis and modeling of complex systems and networks; and solid programming skills necessary to handle big data and develop large scale simulations.

To apply, email/send a CV and names and emails of three references to Tara Holbrook. Applications received by Oct. 24, 2011 will be given full consideration, but the position will remain open until a successful candidate is identified.

Indiana University is an Equal Opportunity/Affirmative Action employer. Applications from women and minorities are strongly encouraged. IU Bloomington is vitally interested in the needs of Dual Career couples.

Thanks to KDnuggets, SOCNET, Gephi, DBWorld, Air-L, CITASA and others for help in advertising this position.

Truthy tool identifies smear tactics on Twitter

Astroturfers, Twitter-bombers and smear campaigners need beware this election season as a group of leading Indiana University information and computer scientists today unleashed Truthy.indiana.edu, a sophisticated new Twitter-based research tool that combines data mining, social network analysis and crowdsourcing to uncover deceptive tactics and misinformation leading up to the Nov. 2 elections. Combing through thousands of tweets per hour in search of political keywords, the team based out of IU’s School of Informatics and Computing will isolate patterns of interest and then insert those memes (ideas or patterns passed by imitation) into Twitter’s application programming interface (API) to obtain more information about the meme’s history.

In the run-up to the mid-term elections, Truthy uncovered a number of abuses such as robot-driven traffic to politician websites and networks of bot accounts controlled by individuals to promote fake news. These findings have been widely covered in the press, with mentions in The Atlantic, MIT Technology Review, PC World, New Scientist, NPR, Ars Technica, Fast Company, The Chronicle of Higher Education, The New York Times Magazine, and many other media. Read more here and here.

CNetS Associate Professor Johan Bollen interviewed on CNBC and CNN for his work on sentiment tracking via Twitter

Johan Bollen discussed his findings that the public’s collective mood as expressed on Twitter correlates in a surprising way to the performance of the Dow Jones Industrial Average today on CNBC’s Squawk on the Street and CNN International’s Quest Means Business. Bollen explained that contrary to expectations, the public’s overall anxiety appears to predict DJIA closing values three to four days in advance, rather than following from DJIA performance.

The interview draws from a paper authored by Bollen and colleagues called “Twitter Mood Predicts the Stock Market” wherein the researchers presented their findings after applying the Google-Profile of Mood States (GPOMS) algorithm to 9.7 million tweets between March and December 2008. The algorithm measures public mood by analyzing the textual content of Tweets before indexing that content into one of six mood states. One of the mood states “calmness” was demonstrated to be significantly predictive of market performance.