Sitaram (Ram) Asur

Researcher
Palo Alto

Biography



Sitaram Asur is a researcher at the Social Computing Research Group at HP Labs. He joined HP Labs as part of the 2009 NSF Computation Innovations Fellowship. Prior to that, he received his PhD. in Computer Science from the Ohio State University in 2009. He is the author of more than 20 conference and journal publications and has received the Best Application Paper award at SIGKDD 2007. He has also authored several industry patents and has served in the Program Committee of numerous conferences and workshops. He organized the Workshop on Dynamic Network Analysis (DNA-SDM) at the Siam Data Mining Conference 2012.

 

Research interests

Social Computing, Data Mining, Machine Learning, Information Retrieval, Natural Language Processing



Recent Research:

  • Predicting Box-Office Revenue using Social MediaIn this work, we demonstrate how social media content can be used to predict real-world outcomes. We use real-time chatter from Twitter.com to forecast box-office revenues for movies. We show that a simple model built from the rate at which tweets are created about particular topics can outperform market-based predictors. We further demonstrate how sentiments extracted from Twitter can be further utilized to improve the forecasting power of social media.This work was published in ACM WI 2010. It was also featured in several news articles including the BBC, Los Angeles Times, and the New York Times Magazine: The 10th Annual Year in Ideas. It was also featured in the cover story of the New Scientist (July 24, 2010). 
  • Measuring Social InfluenceWe proposed an algorithm that determines the influence and passivity of users on a social network based on their information forwarding activity. An evaluation performed with a 2.5 million user dataset on Twitter shows that our influence measure is a good predictor of URL clicks, outperforming several other measures that do not explicitly take user passivity into account. We demonstrate that high popularity does not necessarily imply high influence and vice-versa.This work was featured in the Economist, BBC, FastCompany and other news media. It was also featured in Socialmedia.net: The Best of 2010. 
  • Trends in Social MediaIn this work, we conducted an intensive study of trending topics on Twitter and provided a theoretical basis for the formation, persistence and decay of trends. We also demonstrated empirically how factors such as user activity and number of followers do not contribute strongly to trend creation and its propagation. In fact, we found that the resonance of the content with the users of the social network plays a major role in causing trends. Furthermore, we found that the content that trended was largely news from traditional media sources such as CNN and the New York Times, which were then amplified by repeated retweets on Twitter to generate trends.

Awards

  • 26th in Fast Company's 100 Most Creative People in Business 2011
  • Computing Innovations Fellowship Award, NSF, 2009  
  • Outstanding Research Award, Dept of Computer Science and Engineering, Ohio State University, 2009
  • Best Application Paper Award, SIGKDD, 2007
  • University Fellowship, Ohio State University, 2003

Publications

Journal Publications:

  • S. Asur, S. Parthasarathy and D. Ucar. An Event-based Framework for Characterizing the Evolutionary Behavior of Interaction Graphs. In Transactions of Knowledge Discovery and Data Mining (TKDD) 2009.  
  • S. Asur, D. Ucar and S. Parthasarathy. An Ensemble Framework for Clustering Protein-Protein Interaction Networks In Bioinformatics Volume 23, i29-i40. July 2007.     
  • S. Asur, P. Raman, M. Otey and S. Parthasarathy.A Model-based Approach for Mining Membrane Protein Crystallization Trials In Bioinformatics Volume 22(14), e40-e48. July 2006.   
Conference/Workshop Publications:  
  • C. Wagner, S. Asur and J. Hailpern. Religious Politicians and Creative Photographers: Automatic User Categorization in Twitter. In the Proceedings of the 2013 ASE/IEEE International Conference on Social Computing (SocialCom), 2013.
  • R. Ghosh and S. AsurMining Information from Heterogeneous Sources:  A Topic Modeling Approach. In the Proceedings of the MDS Workshop at the 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (MDS-SIGKDD), 2013.
  • F. Chua and S. Asur. Automatic Summarization of Events from Social MediaIn the Proceedings of the 7th International AAAI Conference on Weblogs and Social Media (ICWSM), 2013. 
  • R. Bandari, S. Asur and B. A. Huberman. The Pulse of News in Social Media : Forecasting Popularity. In the Proceedings of the 6th International AAAI Conference on Weblogs and Social Media (ICWSM), 2012. 
  •  D. M. Romero, W. Galuba, S. Asur and B. A. Huberman. Influence and Passivity in Social Media. In the Proceedings of the European Conference on Machine Learning and Principles and Practices of Knowledge Discovery in Databases (ECML-PKDD), 2011.    
  • L. Yu, S. Asur and B. A. Huberman. What Trends in Chinese Social MediaIn the Proceedings of the 5th Workshop on Social Network Mining and Analysis at the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), 2011.                                                                    
  • S. Asur, B. A. Huberman, G. Szabo and C. Wang. Trends in Social Media : Persistence and DecayIn the Proceedings of the 5th International Conference on Weblogs and Social Media (ICWSM), 2011.
  •  D. M. Romero, W. Galuba, S. Asur and B. A. Huberman. Influence and Passivity in Social MediaIn the Proceedings of the 20th International Conference on World Wide Web (WWW), 2011.  
  • S. Asur and B. A. Huberman. Predicting the Future With Social MediaIn the Proceedings of the ACM International Conference on Web Intelligence, 2010. 
  • S. Asur and S. Parthasarathy. A Viewpoint-based Approach for Interaction Graph AnalysisTo Appear in the Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(SIGKDD), 2009.  
  •  X. Yang, S. Asur, S. Parthasarathy and S. Mehta. A Visual-Analytic Toolkit for Dynamic Interaction GraphsIn the Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), 2008. 
  •  S. Asur, S. Parthasarathy and D. Ucar. An Event-based Framework for Characterizing the Evolutionary Behavior of Interaction GraphsIn the Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), 2007 - Winner of Best Application Paper Award. 
  • S. Asur and S. Parthasarathy. Correlation-based Feature Partitioning for Rare Event Detection in Wireless Sensor NetworksIn the Proceedings of the 1st ACM Workshop on Knowledge Discovery from Sensor Data at the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(Sensor-KDD), 2007. 
  • S. Asur, D. Ucar and S. Parthasarathy. An Ensemble Framework for Clustering Protein-Protein Interaction NetworksIn the Proceedings of the 15th Annual International Conference on Intelligent Systems(ISMB), 2007.  
  •  D. Ucar, S. Parthasarathy and S. AsurNovel Pre-processing Techniques to Improve Functional Modularity in Protein-Protein Interaction Graphs 13th International Conference on Intelligent Systems for Molecular Biology (ISMB), 2007. 
  •  D. Ucar, S. Asur, U. Catalyurek and S. Parthasarathy. Improving Functional Modularity in Protein-Protein Interactions Graphs Using Hub-induced SubgraphsIn the Proceedings of the European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), 2006.  
  •  S. Asur, S. Parthasarathy and D. Ucar, An Ensemble Approach for Clustering Scale-Free Graphs In the Proceedings of the LinkKDD workshop at the ACM International Conference on Knowledge Discovery and Data Mining (LinkKDD), 2006. 
  • S. Asur, P. Raman, M. Otey and S. Parthasarathy. A Model-based Approach for Mining Membrane Protein Crystallization TrialsIn the proceedings of the 14th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB), 2006.   
  • D. Ucar, S. Parthasarathy, S. Asur and C. Wang, Effective Pre-processing Strategies for Functional Clustering of a Protein-Protein Interactions NetworkIn the Proceedings of the IEEE 5th Symposium on Bioinformatics and Bioengineering(BIBE), 2005.

Professional activities

  • Program Committee Member :  ECML/PKDD 2010, COMAD 2009-2010, SIGKDD 2011-12, SocMed 2011, SocInfo 2011-13, WWW 2012, ICWSM 2013, CIKM 2013, ICDE 2013
  • Reviewer : BIBE 2005, SIGKDD 2006-2009, ICDM 2005-2006, SIGMOD 2007, CIKM 2007, WWW 2008-2010, ICDE 2009, TKDD 2010, TKDE 2010, ICDM 2010