Deep Agent: Studying the Dynamics of Information Spread and Evolution in Social Networks

Garibay, Iván; Oghaz, Toktam A.; Yousefi, Niloofar; Mutlu, Ece C.; Schiappa, Madeline C.; Scheinert, Steven R.; Anagnostopoulos, Georgios C.; Bouwens, Christina; Fiore, Stephen M.; Mantzaris, Alexander V.; Murphy, John T.; Rand, William; Salter, Anastasia; Stanfill, Mel; Sukthankar, Gita; Baral, Nisha; Fair, Gabriel; Gunaratne, Chathika; Hajiakhoond, Neda; Jasser, Jasser; Jayalath, Chathura; Newton, Olivia B.; Saadat, Samaneh; Senevirathna, Chathurani; Winter, Rachel; Xi, Zhang

doi:10.1007/978-3-030-77517-9_11

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this model did not allow for anything less than a full adoption after enough time transpires and did not consider the impact of opposing groups' on adoption. Additionally, Garibay et al (2021) provides a framework for modeling information spread on social networks using agent-based models.…”

Section: 13mentioning

confidence: 99%

Network Structure Can Amplify Innovation Adoption and Polarization in Group-Structured Populations with Outgroup Aversion

Miller,

Garibay,

Baggio

et al. 2023

JASSS

View full text Add to dashboard Cite

Individuals' decisions to adopt an innovation can be influenced by the frequency of other adopters as well as by the group membership of previous adopters or non-adopters in their social network. In addition, adoption or non-adoption of some innovations has been characterized as a means of signaling identification with a group. While identity signaling and outgroup aversion effects on adoption and polarization have been considered in a geo-spatial environment, this work extends an existing model of outgroup aversion to a network-based environment. The results show that adoption levels in a network environment were higher, and polarization lower compared to the non-network environment with all other factors fixed. As more factors were varied, the associated change to adoption and polarization were amplified in network environments. The two most significant factors influencing adoption variability were the degree of outgroup aversion and the level of frequency dependence. Finally, in network environments with outgroup aversion, adoption was found to be higher when modularity and eigenvector centrality were high. In today's polarized social environment, understanding these effects is critical to the adoption of emerging innovations such as mitigating climate change, combating novel viruses, or decentralizing financial transactions. While innovators are often focused on solving technical challenges to advance adoption of an innovation, equal emphasis on understanding and solving social and potential outgroup effects will be needed to achieve a desired adoption level.

show abstract

Section: 13mentioning

confidence: 99%

Network Structure Can Amplify Innovation Adoption and Polarization in Group-Structured Populations with Outgroup Aversion

Miller,

Garibay,

Baggio

et al. 2023

JASSS

View full text Add to dashboard Cite

show abstract

“…The works of [17] and [18] use neural networks on sequences of adjacency matrices to predict user activity over time in Twitter. In [19] the authors use a novel method that combines social science theory with a preferential attachement model.…”

Section: Direct User-level Prediction In Social Mediamentioning

confidence: 99%

Simulating User-Level Twitter Activity with XGBoost and Probabilistic Hybrid Models

Mubang¹,

Hall²

2022

Preprint

View full text Add to dashboard Cite

The Volume-Audience-Match simulator, or VAM was applied to predict future activity on Twitter related to international economic affairs. VAM was applied to do timeseries forecasting to predict the: (1) number of total activities, (2) number of active old users, and (3) number of newly active users over the span of 24 hours from the start time of prediction. VAM then used these volume predictions to perform user link predictions. A user-user edge was assigned to each of the activities in the 24 future timesteps. VAM considerably outperformed a set of baseline models in both the time series and user-assignment tasks.

show abstract

“…Bhattacharya et al ( 2019 ) proposed an ABM that incorporates social and cognitive agents that model online human-decision making. Garibay et al ( 2020 ) proposed DeepAgent that can simulate social dynamics in a multi-resolution setting at the user, community, population, and content levels. Murić et al ( 2022 ) developed an ABM that provides support for simulations of cognitive behavior and shared state across multiple compute nodes.…”

Section: Introductionmentioning

confidence: 99%

Modeling information diffusion in social media: data-driven observations

et al. 2023

View full text Add to dashboard Cite

Accurately modeling information diffusion within and across social media platforms has many practical applications, such as estimating the size of the audience exposed to a particular narrative or testing intervention techniques for addressing misinformation. However, it turns out that real data reveal phenomena that pose significant challenges to modeling: events in the physical world affect in varying ways conversations on different social media platforms; coordinated influence campaigns may swing discussions in unexpected directions; a platform's algorithms direct who sees which message, which affects in opaque ways how information spreads. This article describes our research efforts in the SocialSim program of the Defense Advanced Research Projects Agency. As formulated by DARPA, the intent of the SocialSim research program was “to develop innovative technologies for high-fidelity computational simulation of online social behavior ... [focused] specifically on information spread and evolution.” In this article we document lessons we learned over the 4+ years of the recently concluded project. Our hope is that an accounting of our experience may prove useful to other researchers should they attempt a related project.

show abstract

Deep Agent: Studying the Dynamics of Information Spread and Evolution in Social Networks

Cited by 7 publications

References 14 publications

Network Structure Can Amplify Innovation Adoption and Polarization in Group-Structured Populations with Outgroup Aversion

Network Structure Can Amplify Innovation Adoption and Polarization in Group-Structured Populations with Outgroup Aversion

Simulating User-Level Twitter Activity with XGBoost and Probabilistic Hybrid Models

Modeling information diffusion in social media: data-driven observations

Contact Info

Product

Resources

About