The proliferation of social media -- such as Twitter, Facebook, blogs, and Web forums -- has created an unprecedented, continuous stream of messages containing the thoughts, opinions, and beliefs of millions of people. In addition to the primary benefit users of this technology enjoy, a secondary benefit is emerging as scientists discover how to analyze this new data source to provide insights into society. Evidence is mounting that such analysis can be valuable in understanding public health, finance, politics, social unrest, and natural disasters.

The goal of my research is two-fold: (1) to leverage this unprecedented source of data to advance research in automated processing of informal human communication; and (2) to apply these techniques to analyze trends in social media and produce socially beneficial technology. My research contributions can be categorized into three main areas:

• Social Media Analysis: Our work has found surprising correlations between Twitter chatter and values such as the influenza rate, alcohol sales volume, and the level of concern towards an impending hurricane.
• Information extraction and Data mining: We have investigated several statistical algorithms to extract facts and patterns from unstructured text, focusing on the fundamental problems of coreference resolution, relation extraction, and canonicalization.
• Machine learning: The difficulty of the above applications has driven research in novel graphical modeling methods that are built to scale to problems with a large number of complex dependencies. We have also invented new active learning algorithms specifically tailored for these tasks.

Press: Our work in social media analysis has been discussed in several press outlets, including the Wall Street Journal, The Atlantic, CNET, and the Communcations of the ACM.

(see also my Google Scholar page)

2012	A demographic analysis of online sentiment during Hurricane Irene Benjamin Mandel, Aron Culotta, John Boulahanis, Danielle Stark, Bonnie Lewis, Jeremy Rodrigue NAACL-HLT Workshop on Language in Social Media, 2012
	Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages Aron Culotta Language Resources and Evaluation, Special Issue on Analysis of Short Texts on the Web, 2012 Preprint. Final version available at springer.com
2011	SampleRank: Training factor graphs with atomic gradients Michael Wick, Khashayar Rohanimanesh, Kedar Bellare, Aron Culotta, Andrew McCallum Proceedings of the International Conference on Machine Learning (ICML), 2011
2010	Detecting influenza epidemics by analyzing Twitter messages Aron Culotta arXiv:1007.4748v1 [cs.IR], 2010
	Towards detecting influenza epidemics by analyzing Twitter messages Aron Culotta KDD Workshop on Social Media Analytics, 2010
2009	SampleRank: Learning preferences from atomic gradients Michael Wick, Khashayar Rohanimanesh, Aron Culotta, Andrew McCallum Neural Information Processing Systems (NIPS) Workshop on Advances in Ranking, 2009
	An entity-based model for coreference resolution Michael Wick, Aron Culotta, Khashayar Rohanimanesh, Andrew McCallum SIAM International Conference on Data Mining, 2009
2008	Learning and inference in weighted logic with application to natural language processing Aron Culotta Ph.D. Thesis, University of Massachusetts, Amherst, 2008
2007	Canonicalization of Database Records using Adaptive Similarity Measures Aron Culotta, Michael Wick, Robert Hall, Matthew Marzilli, Andrew McCallum Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2007
	Sparse Message Passing Algorithms for Weighted Maximum Satisfiability Aron Culotta, Andrew McCallum, Bart Selman, Ashish Sabharwal New England Student Colloquium on Artificial Intelligence (NESCAI), 2007
	Author Disambiguation using Error-driven Machine Learning with a Ranking Loss Function Aron Culotta, Pallika Kanani, Robert Hall, Michael Wick, Andrew McCallum Sixth International Workshop on Information Integration on the Web (IIWeb-07), 2007
	First-Order Probabilistic Models for Coreference Resolution Aron Culotta, Michael Wick, Robert Hall, Andrew McCallum Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2007
2006	Corrective Feedback and Persistent Learning for Information Extraction Aron Culotta, Trausti Kristjansson, Andrew McCallum, Paul Viola Artificial Intelligence, 2006
	Tractable Learning and Inference with High-Order Representations Aron Culotta, Andrew McCallum International Conference on Machine Learning Workshop on Open Problems in Statistical Relational Learning, 2006
	Learning field compatibilities to extract database records from unstructured text Michael Wick, Aron Culotta, Andrew McCallum Conference on Empirical Methods in Natural Language Processing (EMNLP), 2006
	Practical Markov logic containing first-order quantifiers with application to identity uncertainty Aron Culotta, Andrew McCallum Human Language Technology Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing (HLT/NAACL), 2006
	Integrating probabilistic extraction models and data mining to discover relations and patterns in text Aron Culotta, Andrew McCallum, Jonathan Betz Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2006
2005	Learning clusterwise similarity with first-order features Aron Culotta, Andrew McCallum Neural Information Processing Systems (NIPS) Workshop on the Theoretical Foundations of Clustering, 2005
	A conditional model of deduplication for multi-type relational data Aron Culotta, Andrew McCallum University of Massachusetts IR-443, 2005
	Joint deduplication of multiple record types in relational data Aron Culotta, Andrew McCallum ACM CIKM International Conference on Information and Knowledge Management, 2005
	Reducing labeling effort for structured prediction tasks Aron Culotta, Andrew McCallum The Twentieth National Conference on Artificial Intelligence (AAAI), 2005
	Gene prediction with conditional random fields Aron Culotta, David Kulp, Andrew McCallum University of Massachusetts, Amherst UM-CS-2005-028, 2005
2004	Dependency tree kernels for relation extraction Aron Culotta, Jeffery Sorensen 42nd Annual Meeting of the Association for Computational Linguistics (ACL), 2004
	Interactive information extraction with constrained conditional random fields Trausti Kristjannson, Aron Culotta, Paul Viola, Andrew McCallum Nineteenth National Conference on Artificial Intelligence (AAAI), 2004 Best Paper Award (Honorable Mention)
	Confidence estimation for information extraction Aron Culotta, Andrew McCallum Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT/NAACL), 2004
	Extracting social networks and contact information from email and the Web Aron Culotta, Ron Bekkerman, Andrew McCallum First Conference on Email and Anti-Spam (CEAS), 2004
2003	Maximizing cascades in social networks Aron Culotta University of Massachusetts, 2003

Spring 2013	CS207: Programming II [schedule] CS300: Client-side Web Development [schedule]
Fall 2012	CS207: Programming II CS300: Client-side Web Development

Courses taught at previous instututions:

• Machine Learning
• Automata & Formal Languages
• Fundamental Algorithms
• Simulation & Modeling
• Integrated Technologies for Enterprise Systems

Some data sets I've created to train and evaluate machine learning algorithms:

• Rexa Coreference
• Contact Record Extraction
• Wikipedia Relation Extraction
• Publication Venue Canonicalization
• ACE Coreference