aron culotta    [cv]
associate professor of computer science
illinois institute of technology



I investigate computational methods to learn about human behavior from online social networks.

Examples include tracking diseases, measuring effectiveness of public health campaigns, informing crisis response, preventing online harassment, detecting deceptive marketing, and identifying unsafe products.

The methods rely on machine learning, natural language processing, social network analysis, causal inference, and time series modeling. See our lab page for more.

I am always open to collaboration, particularly with social scientists.

Are you a student interested in a phd or independent study?

teaching

online social network analysis
natural language processing
information retrieval

funding

This research is made possible in part by the National Science Foundation, the Nayar Prize, and the Educational and Research Initiative at Illinois Tech. I am grateful for this support.

awards

nayar prize ii finalist
outstanding paper honorable mention, aaai
best paper honorable mention, cscw
teacher of the year, computer science department, illinois tech
microsoft live labs fellow

publications       [google scholar]

When do words matter? Understanding the Impact of Lexical Choice on Audience Perception using Individual Treatment Effect Estimation
Zhao Wang, Aron Culotta
AAAI, 2019
Discovering and Controlling for Latent Confounds in Text Classification Using Adversarial Domain Adaptation
Virgile Landeiro, Tuan Tran, Aron Culotta
SDM, 2019
Collecting Representative Samples from a Search Engine by Adaptive Query Generation
Virgile Landeiro, Aron Culotta
ASONAM, 2019
Estimating Tie Strength in Follower Networks to Measure Brand Perceptions
Tung Nguyen, Li Zhang, Aron Culotta
FAB, 2019
Personality and Behavior in Role-based Online Games
Zhao Wang, Anna Sapienza, Aron Culotta, Emilio Ferrara
COG, 2019
Robust Text Classification under Confounding Shift
Virgile Landeiro, Aron Culotta
JAIR, 2018
code
Forecasting the presence and intensity of hostility on Instagram using linguistic and social features
Ping Liu, Joshua Guberman, Libby Hemphill, Aron Culotta
ICWSM, 2018
code
Learning from noisy label proportions for classifying online social data
Ehsan Mohammady Ardehaly, Aron Culotta
SNAM, 2018
Mining the Demographics of Political Sentiment from Twitter Using Learning from Label Proportions
Ehsan Ardehaly, Aron Culotta
ICDM, 2017
Co-training for Demographic Classification Using Deep Learning from Label Proportions
Ehsan Ardehaly, Aron Culotta
ICDM-WS, 2017
Are Words Commensurate with Actions? Quantifying Commitment to a Cause from Online Public Messaging
Zhao Wang, Jennifer Cutler, Aron Culotta
ICDM-WS, 2017
code
Controlling for Unobserved Confounds in Classification Using Correlational Constraints
Virgile Landeiro, Aron Culotta
ICWSM, 2017
code
Identifying leading indicators of product recalls from online reviews using positive unlabeled learning and domain adaptation
Shreesh Kumara Bhat, Aron Culotta
ICWSM, 2017
code
Using online social networks to measure consumers’ brand perception
Jennifer Cutler, Aron Culotta
Applied Marketing Analytics, 2017
Towards identifying leading indicators of smoking cessation attempts from social media
Aron Culotta
ICHI-WS, 2016
Polar Scores: Measuring Partisanship Using Social Media Content
Libby Hemphill, Aron Culotta, Matthew Heston
Journal of Information Technology & Politics, 2016
code
Cold-start recommendations for audio news stories using matrix factorization
Ehsan Mohammady Ardehaly, Aron Culotta
IJCAI, 2016
Domain adaptation for learning from label proportions using self-training
Ehsan Mohammady Ardehaly, Aron Culotta
IJCAI, 2016
Training a text classifier with a single word using Twitter Lists and domain adaptation
Aron Culotta
SNAM, 2016
Reducing confounding bias in observational studies that use text classification
Virgile Landeiro, Aron Culotta
AAAI Symposium, 2016
Predicting Twitter User Demographics using Distant Supervision from Website Traffic Data
Aron Culotta, Nirmal Kumar Ravi, Jennifer Cutler
JAIR, 2016
code
Mining brand perceptions from Twitter social networks
Aron Culotta, Jennifer Cutler
Marketing Science, 2016
code
Robust text classification in the presence of confounding variables
Virgile Landeiro, Aron Culotta
AAAI, 2016
code
Finding truth in cause-related advertising: A lexical analysis of brands' health, environment, and social justice communications on Twitter
Aron Culotta, Jennifer Cutler, Junzhe Zheng
The Journal of Values-Based Leadership, 2015
A demographic and sentiment analysis of e-cigarette messages on Twitter
Elaine Cristina Resende, Aron Culotta
BCB-WS, 2015
code
Inferring latent attributes of Twitter users with label regularization
Ehsan Mohammady Ardehaly, Aron Culotta
HLT/NAACL, 2015
Using Matched Samples to Estimate the Effects of Exercise on Mental Health from Twitter
Virgile Landeiro Dos Reis, Aron Culotta
AAAI, 2015
code
Predicting the Demographics of Twitter Users from Website Traffic Data
Aron Culotta, Nirmal Ravi Kumar, Jennifer Cutler
AAAI, 2015
code
Reducing Sampling Bias in Social Media Data for County Health Inference
Aron Culotta
JSM, 2014
code
Anytime Active Learning
Maria E Ramirez-Loaiza, Aron Culotta, Mustafa Bilgic
AAAI, 2014
Using county demographics to infer attributes of Twitter users
Ehsan Mohammady, Aron Culotta
ACL-WS, 2014
Tweedr: Mining Twitter to Inform Disaster Response
Zahra Ashktorab, Christopher Brown, Manojit Nandi, Aron Culotta
ISCRAM, 2014
code
Estimating County Health Statistics with Twitter
Aron Culotta
CHI, 2014
code
Inferring the origin location of tweets with quantitative confidence
Reid Priedhorsky, Aron Culotta, Sara Y. Del Valle
CSCW, 2014
code
Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages
Aron Culotta
LREC, 2013
Framing in Social Media: How the US Congress Uses Twitter Hashtags to Frame Political Issues
Libby Hemphill, Aron Culotta, Matthew Heston
Tech Report, 2013
code
Towards Anytime Active Learning: Interrupting Experts to Reduce Annotation Costs
Maria E. Ramirez-Loaiza, Aron Culotta, Mustafa Bilgic
KDD-WS, 2013
Too Neurotic, Not too Friendly: Structured Personality Classification on Textual Data
Francisco Iacobelli, Aron Culotta
ICWSM-WS, 2013
A demographic analysis of online sentiment during Hurricane Irene
Benjamin Mandel, Aron Culotta, John Boulahanis, Danielle Stark, Bonnie Lewis, Jeremy Rodrigue
NAACL/HLT-WS, 2012
SampleRank: Training factor graphs with atomic gradients
Michael Wick, Khashayar Rohanimanesh, Kedar Bellare, Aron Culotta, Andrew McCallum
ICML, 2011
Detecting influenza epidemics by analyzing Twitter messages
Aron Culotta
Tech Report, 2010
Towards detecting influenza epidemics by analyzing Twitter messages
Aron Culotta
KDD-WS, 2010
SampleRank: Learning preferences from atomic gradients
Michael Wick, Khashayar Rohanimanesh, Aron Culotta, Andrew McCallum
NIPS-WS, 2009
An entity-based model for coreference resolution
Michael Wick, Aron Culotta, Khashayar Rohanimanesh, Andrew McCallum
SDM, 2009
Learning and inference in weighted logic with application to natural language processing
Aron Culotta
PhD Thesis, 2008
Canonicalization of Database Records using Adaptive Similarity Measures
Aron Culotta, Michael Wick, Robert Hall, Matthew Marzilli, Andrew McCallum
KDD, 2007
Sparse Message Passing Algorithms for Weighted Maximum Satisfiability
Aron Culotta, Andrew McCallum, Bart Selman, Ashish Sabharwal
NESCAI, 2007
Author Disambiguation using Error-driven Machine Learning with a Ranking Loss Function
Aron Culotta, Pallika Kanani, Robert Hall, Michael Wick, Andrew McCallum
IIWeb, 2007
First-Order Probabilistic Models for Coreference Resolution
Aron Culotta, Michael Wick, Robert Hall, Andrew McCallum
HLT/NAACL, 2007
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
ICML-WS, 2006
Learning field compatibilities to extract database records from unstructured text
Michael Wick, Aron Culotta, Andrew McCallum
EMNLP, 2006
Practical Markov logic containing first-order quantifiers with application to identity uncertainty
Aron Culotta, Andrew McCallum
HLT/NAACL, 2006
Integrating probabilistic extraction models and data mining to discover relations and patterns in text
Aron Culotta, Andrew McCallum, Jonathan Betz
HLT/NAACL, 2006
Learning clusterwise similarity with first-order features
Aron Culotta, Andrew McCallum
NIPS-WS, 2005
A conditional model of deduplication for multi-type relational data
Aron Culotta, Andrew McCallum
Tech Report, 2005
Joint deduplication of multiple record types in relational data
Aron Culotta, Andrew McCallum
CIKM, 2005
Reducing labeling effort for structured prediction tasks
Aron Culotta, Andrew McCallum
AAAI, 2005
Gene prediction with conditional random fields
Aron Culotta, David Kulp, Andrew McCallum
Tech Report, 2005
Dependency tree kernels for relation extraction
Aron Culotta, Jeffery Sorensen
ACL, 2004
Interactive information extraction with constrained conditional random fields
Trausti Kristjannson, Aron Culotta, Paul Viola, Andrew McCallum
AAAI, 2004
Confidence estimation for information extraction
Aron Culotta, Andrew McCallum
HLT, 2004
Extracting social networks and contact information from email and the Web
Aron Culotta, Ron Bekkerman, Andrew McCallum
CEAS, 2004
Maximizing cascades in social networks
Aron Culotta
Tech Report, 2003