Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Dept. of Computer Science; Escuela Superior Politecnica del Litoral (ESPOL), Guayaquil (Ecuador); OSTI
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Dept. of Statistics
Brookhaven National Lab. (BNL), Upton, NY (United States). Computational Science Initiative
Northwestern Univ., Evanston, IL (United States). Dept. of Industrial Engineering and Management Sciences
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
New York Univ. (NYU), NY (United States). Dept. of Epidemiology
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Biocomplexity Inst.
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Biocomplexity Inst. & Initiative
Cornell Univ., Ithaca, NY (United States). Dept. of Sociology
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Biocomplexity Inst. & Initiative; Univ. of Virginia, Charlottesville, VA (United States). Dept. of Computer Science
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Dept. of Computer Science; Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Discovery Analytics Center
Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). Discovery Analytics Center
There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.
@article{osti_1815434,
author = {Cedeno-Mieles, Vanessa and Hu, Zhihao and Ren, Yihui and Deng, Xinwei and Contractor, Noshir and Ekanayake, Saliya and Epstein, Joshua M. and Goode, Brian J. and Korkmaz, Gizem and Kuhlman, Chris J. and others},
title = {Data analysis and modeling pipelines for controlled networked social science experiments},
annote = {There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.},
doi = {10.1371/journal.pone.0242453},
url = {https://www.osti.gov/biblio/1815434},
journal = {PLoS ONE},
issn = {ISSN 1932-6203},
number = {11},
volume = {15},
place = {United States},
publisher = {Public Library of Science},
year = {2020},
month = {11}}
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Organization:
USDOE Office of Science (SC); Defense Advanced Research Projects Agency (DARPA); Defense Threat Reduction Agency (DTRA); National Science Foundation (NSF); US Army Research Laboratory (USARL)
2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)https://doi.org/10.1109/ASONAM.2014.6921602
2010 4th International Conference on Network and System Security (NSS), 2010 Fourth International Conference on Network and System Securityhttps://doi.org/10.1109/NSS.2010.72
LAK '16: 6th International Conference on Learning Analytics and Knowledge, Proceedings of the Sixth International Conference on Learning Analytics & Knowledgehttps://doi.org/10.1145/2883851.2883912
ASONAM '19: International Conference on Advances in Social Networks Analysis and Mining, Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mininghttps://doi.org/10.1145/3341161.3342965