DARPA SocialSim: Deep Agent: A Framework for Information Spread and Evolution in Social Networks

For this project, we will build a comprehensive, realistic and at-scale computational simulation of information spread and evolution in online social networks using a novel computational modeling paradigm: Deep Agent Framework (DAF). The Deep Agent Framework unleashes the power of combining massively parallel computing, data analytics of large datasets and machine learning into assisting model designers to mix and match sub models in a semi-automated way, exploring, testing and validating not one but tens of thousands of models against not a single real world phenomenon but a large set of target behaviors. This process will aid model designers to continuously improve the best-so-far model as the problem challenges become more difficult. In fact, this process would also serve to automatically recombine and introduce variants to all the models produced by different TA1 performers in order to obtain the overall best model. This framework will enable the creation of an accurate and at-scale simulation of information spread and evolution that can run on a typical off-the shelf commercial computer or small cluster.
Partially as a result of this project, the Inverse Generative Social Science (iGSS) community was formed: Inverse Generative Social Science Workshop 2021, Inverse Generative Social Science Workshop 2021.

	Defense Advance Research Projects Agency (DARPA) Computational Simulation of Online Social Behavior (SocialSim), PM: Dr.Brian Kettler Award Number: FA865018C7823 Principal Investigator: Ivan Garibay $6,200,000.00 October 2017-December 2021 [Project Website] [PDF] [SocialSim Program] [DARPA]

Collaborators

	William Rand Associate Professor of Marketing North Carolina State University Department of Business Management [Website]		Stephen M. Fiore Professor University of Central Florida Department of Philosophy [Website]
	Gita Reese Sukthankar Associate Professor University of Central Florida Department of Computer Science [Website]		Alexander Mantzaris Assistant Professor University of Central Florida Department of Statistics & Data Science [Website]
	John T. Murphy Research Associate Professor Northern Illinois University University of Chicago/Argon Nat. Lab. Department of Archaeology [Website]		Joshua Epstein Professor of Epidemiology New York University NYU School of Global Public Health [Website]

Selected Related Publications

	Inferring mechanisms of response prioritization on social media under information overload. Chathika Gunaratne, William Rand, and Ivan Garibay 2021 Scientific Reports, 11, 1346. [Journal]
	Influence Cascades: Entropy-Based Characterization of Behavioral Influence Patterns in Social Media. Chathurani Senevirathna, Chathika Gunaratne, William Rand, Chathura Jayalath, and Ivan Garibay 2021 Entropy, 23(2), 160 [Journal]
	Evolutionary model discovery of causal factors behind the socio-agricultural behavior of the Ancestral Pueblo. Gunaratne, C. and Garibay, I. 2020 PLoS ONE, 15(12): e0239922. [Journal]
	A stance data set on polarized conversations on Twitter about the efficacy of hydroxychloroquine as a treatment for COVID-19. Ece C. Mutlu, Toktam Oghaz, Jasser Jasser, Ege Tutunculer, Amirarsalan Rajabi, Aida Tayebi, Ozlem Ozmen, and Ivan Garibay 2020 Data in Brief, 33, 106401 [Journal]
	The effects of information overload on online conversation dynamics. Gunaratne, C., Baral, N., Rand, W., Garibay, I., Jayalath, C., and Senevirathna, C. 2020 Computational and Mathematical Organization Theory, 26, 255-276. [Journal]
	Review on Learning and Extracting Graph Features for Link Prediction. Ece C. Mutlu, Toktam Oghaz, Amirarsalan Rajabi and Ivan Garibay 2020 Machine Learning and Knowledge Extraction, 2(4), 672-704. [Journal]
	Modeling social coding dynamics with sampled historical data Bidoki, N. H., Schiappa, M., Sukthankar, G., and Garibay, I. 2020 Online Social Networks and Media, 16:100070. [Journal] [Request Reprint]
	Polarization in social media assists influencers to become more influential: analysis and two inoculation strategies Garibay, I., Mantzaris, A., Rajabi, A., and Taylor, C. E. 2019 Scientific Reports, 9:18592. [Journal]
	On countering disinformation with caution: Effective inoculation strategies and others that backfire into community hyper-polarization Rajabi, A., Gunaratne, C., Mantzaris, A. V., and Garibay, I. 2020 In International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS). Springer. (to appear) [Request Reprint]
	Resistance of communities of against conspiracies Rajabi, A., Talebzadehhosseini, S., and Garibay, I. 2020 In Proceedings of the Conference of the Computational Social Science Society of the Americas (CSS2019), Santa Fe, NM. Springer. (to appear) [Request Reprint]
	Negative influence gradients lead to lowered attention span on social networks Baral, N., Gunaratne, C., Jayalath, C., Rand, W., Senevirathna, C., and Garibay, I. 2020 In Proceedings of the Conference of the Computational Social Science Society of the Americas (CSS2019), Santa Fe, NM. Springer. (to appear) [Request Reprint]
	The degree-dependent threshold model: Towards a better understanding of opinion dynamics on online social networks Best Paper Award Mutlu, E. and Garibay, I. 2020 In Proceedings of the Conference of the Computational Social Science Society of the Americas (CSS2019), Santa Fe, NM. Springer. Best paper award (to appear) [Request Reprint]
	Deep agent: A framework for information spread and evolution in social networks Garibay, I., Oghaz, T., Yousefi, N., Mutlu, E., Schiappa, M., et al. 2020 In Proceedings of the Conference of the Computational Social Science Society of the Americas (CSS2019), Santa Fe, NM. Springer. (to appear) [Request Reprint]

Press

	$6.2 Million DARPA Grant Awarded to Dr. Ivan Garibay UCF IEMS [Article]
	$12.5M Grant Will Help Predict Spread of Online Social Behavior BY MARK SCHLUEB UCF Today [Article]