Tag Archives: data mining

DESPIC team presents Bot Or Not demo and six posters at DoD meeting

IU Bot or Bot poster The DESPIC team at the Center for Complex Systems and Networks Research (CNetS) presented a demo of a new tool named BotOrNot at a DoD meeting held in Arlington, Virginia on April 23-25, 2014.  BotOrNot (truthy.indiana.edu/botornot) is a tool to automatically detect whether a given Twitter user is a social bot or a human. Trained on Twitter bots collected by our lab and the infolab at Texas A&M University, BotOrNot analyzes over a thousand features from the user’s friendship network, content, and temporal information in real time and estimates the degree to which the account may be a bot. In addition to the demo, the DESPIC team (including colleagues at the University of Michigan)  presented several posters on Scalable Architecture for Social Media ObservatoryMeme Clustering in  Streaming DataPersuasion Detection in Social StreamsHigh-Resolution Anomaly Detection in Social Streams, and Early Detection and Analysis of Rumors. See more coverage of BotOrNot on PCWorld, IDS, BBCPolitico, and MIT Technology Review.

New York Times and The Good Wife on Socialbots

image by Niv Bavarsky

The Good Wife
A scene from an episode of The Good Wife inspired by our work on socialbots

On August 11, 2013, the New York Times published an article by Ian Urbina with the headline: I Flirt and Tweet. Follow Me at #Socialbot. The article reports on how socialbots (software simulating people on social media) are being designed to sway elections, to influence the stock market, even to flirt with people and one another. Fil Menczer is quoted: “Bots are getting smarter and easier to create, and people are more susceptible to being fooled by them because we’re more inundated with information.”  The article also mentions the Truthy project and some of our 2010 findings on political astroturf.

Inspired by this, the writers of The Good Wife consulted with us on an episode in which the main character finds that a social news site is using a socialbot to bring traffic to the site, defaming her client. The episode aired on November 24, 2013, on CBS (Season 5 Episode 9, “Whack-a-Mole”). Good show!

PIARE (Protein Interaction Abstract Relevance Evaluator)

Research | People | Academics | News and Meetings | Publications-online | Media Mentions | Relevant Conferences

The Protein Interaction Abstract Relevance Evaluation (PIARE) service, was created to implement the binary classifier we produced for the Protein-Protein Interaction Article Classification Task in Biocreative II and Biocreative II.5. Supplementary materials for our Biocreative III paper are available as a zip file with instructions.

Literature Mining
Biomedical Literature Mining

Relevant Publications:

A. Abi-Haidar, J. Kaur, A. Maguitman, P. Radivojac, A. Retchsteiner, K. Verspoor, Z. Wang, and L.M. Rocha [2008]. “Uncovering protein interaction in abstracts and text using a novel linear model and word proximity networks“. Genome Biology. 9(Suppl 2):S11

A. Kolchinsky, A. Abi-Haidar, J. Kaur, A.A. Hamed and L.M. Rocha [2010]. “Classification of protein-protein interaction full-text documents using text and citation network features.IEEE/ACM Transactions On Computational Biology And Bioinformatics, 7(3):400-411. DOI: doi.ieeecomputersociety.org/10.1109/TCBB.2010.55

A. Lourenço, M. Conover, A. Wong, A. Nematzadeh, F. Pan, H. Shatkay, and L.M. Rocha [2011].”A Linear Classifier Based on Entity Recognition Tools and a Statistical Approach to Method Extraction in the Protein-Protein Interaction Literature“. BMC Bioinformatics. 12(Suppl 8):S12. DOI: 10.1186/1471-2105-12-S8-S12.

CASCI

Complex Adaptive Systems and Computational Intelligence

The Complex Adaptive Systems and Computational Intelligence (CASCI) group at Indiana University and the Instituto Gulbenkian de Ciencia works on complex networks & systems and their applications to informatics, biology, health, and social systems. We are particularly interested in the informational properties of natural and artificial systems which enable them to adapt and evolve. This means both understanding how information is fundamental for the evolutionary capabilities of natural systems, as well as abstracting principles from natural systems to produce adaptive information technology.

Our research projects are on complex networks & systems, computational and systems biology, and computational intelligence; all our publications are available online as are news about our group. Additional information available on Luis Rocha’s Website and our group page at the Instituto Gulbenkian de Ciencia.

See our current roster and information on how to join our group. As a group, we are seriously interconnected with other research groups and networks: The Center for Complex Networks and Systems (CNets), the Indiana University Network Science Institute, the Cognitive Science Program, the FLAD Computational Biology Collaboratorium, the Instituto Gulbenkian de Ciência, and the Champalimaud Neuroscience Program.

You are welcome to join our mailing list CASCI-L by sending an email message to list@list.indiana.edu from the address you want to subscribe to the list, with subject line: subscribe CASCI-L Firstname Lastname (leave the message body blank.) More detailed instructions are available.