Research

The BDSS-IGERT team is engaged in an extensive array of research, ranging across the multi-disciplinary scope of the program.

Since 2012, BDSS-IGERT PhD student trainees and affiliates have co-authored over 200 papers and related scientific products (data, software, etc.) that collectively have garnered over 1400 citations. For details on this research, please see the BDSS-IGERT Google Scholar Page or follow the thematic links below. (Please see individual faculty pages for details on social data analytics research in the broader PSU community.)

Much of this research comes from the required 'research rotations' which are a part of the two year experience for each of the trainees.  Interested faculty can host one or more of the IGERT trainees in their lab/research group for 1-2 semesters to work on research questions that have big data and social science aspects (recent examples here) These are now largely arranged through the 'matchmaking' event held each fall semester. The first was held on September, 2014, and the last was held in September, 2017. 

In addition, the BDSS IGERT team is always open to working on projects that would or might fit the big data and social science aspects of the program's core mission. Projects where groups of students can collaborate, or that might serve as the basis of a 'hackathon' or other form of challenge event. Coming from varying backgrounds -- current IGERT Trainees are from Political Science, Sociology, Criminology, Demography, Human Development & Family Studies, Statistics, Geography, and Informatics -- BDSS IGERT Trainees can bring a unique set of skills and expertise to bear on a problem or research question.

Interested faculty should contact the Program PI, Burt Monroe, (burtmonroe@psu.edu) with a brief description and we will be happy to set up a time to discuss the options.

BDSS-IGERT Research
Collaborating remotely: an evaluation of immersive capabilities on spatial experiences and team membership (International Journal of Digital Earth, 2018)
Citizen monitoring during hazards: validation of Fukushima radiation measurements (GeoJournal, 2018)
Text preprocessing for unsupervised learning: Why it matters, when it misleads, and what to do about it (Political Analysis, 2018)
General and specific utility measures for synthetic data (Royal Statistical Society Series A, 2018)
The evolution of youth friendship networks from 6th to 12th grade: School transitions, popularity and centrality (Social Networks & the Life Course, 2018)
Falling behind: lingering costs of the high school transition for youth friendships and grades (Sociology of Education, 2018)
Feature selection methods for optimal design of studies for developmental inquiry (Journals of Gerontology: Series B, 2018)
More than counting: An intraindividual variability approach to categorical repeated measures (Journals of Gerontology: Series B, 2018)
Learning simpler language models with the differential state framework (Neural Computation, 2017)
Event ordering with a generalized model for sieve prediction ranking (Natural Language Processing, 2017)
Statistical modeling of the default mode brain network reveals a segregated highway structure (Scientific Reports, 2017)
Piecewise latent variables for neural variational text processing (EMNLP, 2017)
Adversary resistant deep neural networks with an application to malware detection (KDD, 2017)
Damage assessment of the urban environment during disasters using volunteered geographic information (Big Data for Regional Science, 2017)
Decision-making in policy governed human-autonomous systems teams (IEEE Smart World Congress, 2017)
Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild (IEEE Computer Vision and Pattern Recognition, 2017)
Smart Library: Identifying books on library shelves using supervised deep learning for scene text reading (Digital Libraries, 2017)
Stochastic weighted graphs: Flexible model specification and simulation (Social Networks, 2017)
NFL draft profiles are full of racial stereotypes. And that matters for when quarterbacks get drafted (Washington Post, 2017)
Statistical models for incorporating data from routine HIV testing of pregnant women at antenatal clinics into HIV/AIDS epidemic estimates (AIDS 2017)
Incorporation of hierarchical structure into estimation and projection package fitting with examples of estimating subnational HIV/AIDS dynamics (AIDS 2017)
Validating Safecast data by comparisons to a U. S. Department of Energy Fukushima Prefecture aerial survey (Journal of Environmental Radioactivity, 2017)
Unifying adversarial training algorithms with data gradient regularization (Neural Computation, 2017)
CompanionViz: Mediated platform for gauging canine health and engancing human-pet interactions (International Journal of Human-Computer Studies, 2017)
Propensity score weighting for a continuous exposure with multilevel data (Health Services and Outcomes Research Methodology, 2016)
Immersive analytics for multi-objective dynamic integrated climate-economy (DICE) models (ACM Interactive Surfaces and Spaces, 2016)
Bag of what? Simple noun phrase extraction for text analysis (EMNLP, NLP + Computational Social Science, 2016)
Using prerequisites to extract concept maps from textbooks (ACM Information and Knowledge Management, 2016)
Racially differentiated language in NFL scouting reports (KDD Large Scale Sports Analytics, 2016)
Inference on the effects of observed features in latent space models for networks (SSRN preprint, 2016)
BDSS-IGERT Research - More…