My methodological research focus on developing statistical methods for routinely collected healthcare databases such as electronic health records (EHR) and claims data. I aim to tackle the unique challenges that arise from the secondary use of real-world data for research purposes. Specifically, I develop novel causal inference methods and semiparametric efficiency theory that harness the full potential of EHR data to address comparative effectiveness and safety questions. I develop scalable and automated pipelines for curation and harmonization of EHR data across healthcare systems and coding systems.
My research interests are in natural language semantics and psycholinguistics, focusing on verbs. I conduct behavioral psycholinguistic experiments with methodologies such as self-paced reading and maze tasks, as well as surveys of linguistic and semantic judgments. I also study semantic variation using corpora and datasets such as the Twitter Decahose, to better understand how words have developed diverging meanings in different communities, age groups, or regions. I use primarily R and Python to collect, manage, and analyze data. I direct the UM WordLab in the linguistics department, working with students (especially undergraduates) on experimental and computational research focusing on lexical representations.
My research is at the intersection of neuroscience and artificial intelligence. My group uses neuroscience or brain-inspired principles to design models and algorithms for computer vision and language processing. In turn, we uses neural network models to test hypotheses in neuroscience and explain or predict human perception and behaviors. My group also develops and uses machine learning algorithms to improve the acquisition and analysis of medical images, including functional magnetic resonance imaging of the brain and magnetic resonance imaging of the gut.
We use brain-inspired neural networks models to predict and decode brain activity in humans processing information from naturalistic audiovisual stimuli.
Greg’s research primarily investigates information flow in financial markets and the actions of agents in those markets – both consumers and producers of that information. His approach draws on theory from the social sciences (economics, psychology and sociology) combined with large data sets from diverse sources and a variety of data science approaches. Most projects combine data from across multiple sources, including commercial data bases, experimentally created data and extracting data from sources designed for other uses (commercial media, web scrapping, cellphone data etc.). In addition to a wide range of econometric and statistical methods, his work has included applying machine learning , textual analysis, mining social media, processes for missing data and combining mixed media.
My research interests span topics in Statistical Machine Learning, Computational Social Science, Natural Language Processing, and Field/Digital Experiments. Substantively, I am interested in understanding the impact of internet technologies on users by empirically studying their interactions with such systems. The research questions that I study are of both predictive as well as causal nature and I examine them by using data from text/natural language and social network domains.
I research how humans behave by observing the things we say, what we do, and who we are. My research combines linguistic analysis and network science together to understand behavior in its natural social context. I collaborate with colleagues from areas such as Psychology, Linguistics, Digital Humanities, and Sociology to improve our theories using data-driven insights and methodologies.
Image caption: Indians use online matrimonial websites to complement the traditional arranged marriage process. Data from these websites can reveal widespread attitudes on caste identity through individuals signaling their openness to marrying someone from a different caste, i.e., intercaste marriage. This figure shows a comparison of demographic factors affecting openness to intercaste marriage in family-posted (left) versus self-posted (right) matrimonial profiles on a major Indian website. Values for each factor reflect a logistic regression coefficients for predicting whether that individual will be open to intercaste marriage. The difference that social status as a function of education, income, affluence, and to some degree caste, drive attitudes, where lower social status individuals are less open to intercaste marriage. Significance levels for model coefficients are reported as ‘***’ for p<0.001 , ‘**’ p<0.01 , and ‘*’ p<0.05, and bars show standard errors. This figure is taken from a paper by
Ashwin Rajadesingan, Ramaswami Mahalingam, David Jurgens, “Smart, Responsible, and Upper Caste Only:Measuring Caste Attitudes through Large-Scale Analysis of Matrimonial Profiles” in the Proceedings of the AAAI International Conference on Web and Social Media (ICWSM), 2019.
Somangshu (Sam) Mukherji, PhD, is Assistant Professor of Music Theory in the School of Music, Theatre & Dance at the University of Michigan, Ann Arbor.
Sam Mukherji‘s work lies at the interface of traditional Western tonal theory, the theory and practice of popular and non-Western idioms, and the cognitive science of music. Within this framework, the main focus of his research has been on the prolongational, grammatical aspects of Western tonality, and their connection to the tonal structures of Indian music, and the blues-based traditions within rock and metal. This emphasis makes his work similar to that of a linguist who explores relationships between the world’s languages-and, therefore, Mukherji’s research has been influenced in particular by ideas from linguistic theory as well, especially the Minimalist Program in contemporary generative linguistics. For this reason, he has investigated connections not only between different musical idioms but also between music and language-and musical and linguistic theory-more generally. Much of his work explores overlaps between Minimalist linguistics, and related, generative approaches within music theory (such as those found in the writings of Heinrich Schenker), and he has also written extensively about what such ‘musicolinguistic’ connections imply for the wider study of human musical behavior, cognition, and evolution.
My research focuses on the intended and unintended consequences of language in financial markets. I examine this relationship across a number of contexts, such as the Federal Reserve, initial public offerings, and mergers and acquisitions. More broadly, my work aims to develop new theoretical and methodological approaches to understand the role of language in society.
V.G.Vinod Vydiswaran, PhD, is Assistant Professor in the Department of Learning Health Sciences with a secondary appointment in the School of Information at the University of Michigan, Ann Arbor.
Dr. Vydiswaran’s research focuses on developing and applying text mining, natural language processing, and machine learning methodologies for extracting relevant information from health-related text corpora. This includes medically relevant information from clinical notes and biomedical literature, and studying the information quality and credibility of online health communication (via health forums and tweets). His previous work includes developing novel information retrieval models to assist clinical decision making, modeling information trustworthiness, and addressing the vocabulary gap between health professionals and laypersons.
Dr. Abney has pursued research in natural language understanding and natural language learning, including information extraction, biomedical text processing, integrating text analysis into web search, robust and rapid partial parsing, stochastic grammars, spoken-language information systems, extraction of linguistic information from scanned page images, dependency-grammar induction for low-resource languages, and semisupervised learning.