Ajita John

Research Scientist

My Research

My research explores the interplay between social media and rich media interactions over audio and video and has proposed live collaborative tagging - a new form of tagging in the enterprise where participants in a conference collaboratively tag the conversation with freely-formed keywords. My research has also explored searching and browsing of tagged rich media and developed computational models for inferring expertise and macro-level properties for user communities in social networks.

I gave a keynote at the 2011 Chicago Colloquium on Digital Humanities and Computer Science. My talk titled Conversations: Then and Now; How Social Media has Changed Interactions and Perspectives focused on the impact of social media feedback for conversations in the enterprise and on Twitter, techniques to integrate the feedback into persisted conversations, and visual perspectives in information retrieval for social media-based content.

I have served on the Technical Program Committees of WWW (Social Network Track) 2012, 2011, 2009, and Hypertext 2010. I am on the Program Committee of the Social Media Track of Hypertext 2012.

In the past, I worked at Bell Labs in the area of network management. I was an adjunct faculty member at the Stevens Institute of Technology in 2002-2003. My Ph.D. dissertation from the Department of Computer Science at The University of Texas at Austin focused on the automatic extraction of parallelism from constraint-based specifications.


Projects

I am working on a project to extract themes from large-scale twitter feeds to public events with Yuheng Hu from Arizona State University.
On a longer term, I have been working on a project called Echoes which can be thought of as a Conversation Pensieve (borrowing from J.K.Rowling's device for storing memories) for audio conversations. Users can store, search, browse, and tag audio conversations (of meetings, discussions, presentations etc.). Users are presented with contextualized networks of conversations, users, and tags when they perform searches in Echoes.

Under a collaboration with Prof. Hari Sundaram and Munmun De Choudhury at Arizona State University, I have worked on projects to analyze:

  • data from social networking websites such as MySpace, Engadget, YouTube, and Digg to infer communication flow
  • how activity in social networks may be correlated with external events
  • how social network dynamics can be characterized at individual, group, and community levels, to infer interestingness of conversations around media objects, and to predict social synchrony in online social media

Under a collaboration with Prof. Alfred Kobsa and Sameer Patil at the University of California at Irvine, I conducted a large field study (extensive audio interviews and online surveys) of a software development project distributed across five geographic locations including one international location. The goal of the study is to understand the factors that affect privacy concerns in using awareness systems and to assess the relationship between awareness and privacy in loosely-coupled collaborations.


Publications

Joint Topic Modeling for Characterizing Public Event and its Twitter Feedback, To appear at the AI and the Web track at the Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI-12), Toronto, Canada, July 2012, Yuheng Hu, Ajita John, Fei Wang, Subbarao Kambhampati 26% acceptance rate.

What were the Tweets about? Topical Associations between Public Events and Twitter Feeds. To appear at the Sixth International AAAI Conference on Weblogs and Social Media (ICWSM 2012), Dublin, Ireland, June 2012. Yuheng Hu, Ajita John, Doree Duncan Seligmann, Fei Wang. 20% acceptance rate

Event Analytics via Social Media. Proc. ACM MM 2011 Workshop on Social and Behavioral Networked Media Access, November 2011. Yuheng Hu, Ajita John, Doree Duncan Seligmann.

Methodological Reflections on a Field Study of a Globally Distributed Software Project in Information and Software Technology, Special Issue on Studying Work Practices in Global Software Engineering, 2011. S. Patil, A. Kobsa, A. John, and D. Seligmann.

Extraction, Characterization and Utility of Prototypical Groups in the Blogosphere. ACM Transactions on Information Systems (TOIS), 2010. M. De. Choudhury, H. Sundaram, A. John, and D. D. Seligmann.

Comparing Privacy Attitudes of Knowledge Workers in the U.S. and India, International Conference on Intercultural Collaboration, Copenhagen, Denmark, August 2010. S. Patil, A. Kobsa, A. John, and D. D. Seligmann.

Some Observations on the Live Tagging of Audio Conferences in the Enterprise, International Conference on Human Factors in Computing Systems (CHI), Atlanta, GA, April  2010. S. Kelkar, A. John, and D. D. Seligmann. 22% acceptance rate

Social Synchrony: Predicting Mimicry of User Actions in Online Social Media. 2009 International Conference on Computational Science and Engineering - Volume 04 (August 29 - 31, 2009). CSE. IEEE Computer Society, Washington, DC, 151-158. M. De Choudhury, H. Sundaram, A. John, and D. D. Seligmann. 9% acceptance rate.

Connecting Content to Community in Social Media via Image Content, User Tags and User Communication. To appear in the Proceedings of the 2009 IEEE International Conference on Multimedia & Expo (Cancun, Mexico, June 28- July 3, 2009). ICME '09. M. De Choudhury, H. Sundaram, Y-R. Lin, A. John, and D. D. Seligmann. 22% acceptance rate

Interpersonal Privacy Management in Distributed Collaboration: Situational Characteristics and Interpretive Influences. The 12th IFIP conference on Human-Computer Interaction: INTERACT 2009, Sweden, August 2009. S. Patil, A. Kobsa, A. John, L. S. Brotman, and D. D. Seligmann. 29% acceptance rate

What Makes Conversations Interesting? Themes, Participants and Consequences of Conversations in Online Social Media. The 18th International World Wide Web Conference (WWW), Madrid, April 2009. M. De Choudhury, H. Sundaram, A. John and D. D. Seligmann. 11% acceptance rate

Can Blog Communication Dynamics be Correlated with Stock Market Activity? The Nineteenth ACM Conference on Hypertext and Hypermedia, Hypertext 08, June, 2008. M. De Choudhury, H. Sundaram, A. John and D. D. Seligmann. 25% acceptance rate
Dynamic Prediction of Communication Flow Using Social Context. The Nineteenth ACM Conference on Hypertext and Hypermedia, Hypertext 08, June. M. De Choudhury, H. Sundaram, A. John and D. D. Seligmann. 25% acceptance rate

Designing for Persistent Audio Conversations in the Enterprise. The Third Designing for User eXperience Conference (DUX 2007), Nov. 2007. A. Renduchintala, S. Kelkar, A. John and D. D. Seligmann.
Contextual Prediction of Communication Flow in Social Networks. The 2007 IEEE/WIC/ ACM International Conference on Web Intelligence, Nov. 2007. M. De Choudhury, H. Sundaram, A. John and D. D. Seligmann. 17% acceptance rate

An Activity-based Perspective of Collaborative Tagging. The International Conference on Weblogs and Social Media (ICWSM), March 2007. S. Kelkar, A. John, and D. D. Seligmann.