Social Network Modeling and Agent-Based Simulation in Support of Crisis De-Escalation

Lanham, Michael; Morgan, Geoffrey P.; Carley, Kathleen M.

doi:10.1109/tsmcc.2012.2230255

Cited by 30 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a combination of complex network, time analysis and agent based modeling was used to understand evolution of organizational relations during response operations [14].…”

mentioning

confidence: 99%

Network based discrete event analysis for coordination processes in crisis response operations

Noori

Paetzold

Vilasís-Cardona

2016

2016 Annual IEEE Systems Conference (SysCon)

View full text Add to dashboard Cite

In this paper we introduce a novel approach to study emerging organizational relations and coordination structures in crisis response operations. We use dynamic modeling methods to analyze operations in conjunction with network analysis to study relationships among coordinating teams. The goal of the research is to produce a model describing evolution of crisis response operation as network based dynamic system. Ultimately, the model should help create different scenarios of cross-organizational collaboration in crisis events to gage effectiveness of crisis response systems. The envisioned research outcome will impact the future design of response plans in crisis management and hopefully contribute to the shift towards decentralized network based response plans.

show abstract

“…Therefore, a combination of complex network, time analysis and agent based modeling was used to understand evolution of organizational relations during response operations [14].…”

mentioning

confidence: 99%

Network based discrete event analysis for coordination processes in crisis response operations

Noori

Paetzold

Vilasís-Cardona

2016

2016 Annual IEEE Systems Conference (SysCon)

View full text Add to dashboard Cite

show abstract

“…Bounded rationality implies that humans cannot recall or process all information available to them, and that the positioning of humans within a social context limits (or otherwise biases) their exposure to all available information. This theory has been used to explain and model how networks evolve over time (Carley, Pfeffer et al, 2012), how behavior mirroring influences consumer decisions (Gloor et al, 2017), methods for de-escalating crises in various online communities (Lanham, Morgan, and Carley, 2013), the effect of malicious bots on information sharing behavior online (Beskow and Carley, 2019;Benigni, Joseph, and Carley, 2019), and the effects of quality management on organizational productivity (Jamshidnezhad and Carley, 2015). By incorporating the propositions of bounded rationality into an agent-based model (ABM), we can better model the emergence of "irrational" phenomena on the internet and in the real world, such as the adamant belief in false information shared online.…”

Section: Theoretical Models Of Information Sharing and Beliefmentioning

confidence: 99%

“…Given the massive amount of information shared online and the proprietary nature of algorithms developed by social media platforms, agent-based modeling (ABM) can be a helpful tool for investigating research questions related to complex human behavior on social networks (Lanham, Morgan, and Carley, 2013;Bonabeau, 2002;Jamshidnezhad and Carley, 2015) and the potential impacts of algorithmic interventions on complex systems (Du et al, 2022). We extend the simulation approach in Beskow and Carley (2019), in which the authors simulated the spread of true and false information online in the presence of strategic bots, after confirming the simulation generates information cascades similar to those found in Vosoughi, Roy, and Aral (2018).…”

Section: Analyzing the Spread Of Misinformation Onlinementioning

confidence: 99%

Does AI-Assisted Fact-Checking Disproportionately Benefit Majority Groups Online?

Neumann¹,

Wolczynski²

2023

Preprint

View full text Add to dashboard Cite

In recent years, algorithms have been incorporated into fact-checking pipelines. They are used not only to flag previously fact-checked misinformation, but also to provide suggestions about which trending claims should be prioritized for fact-checking -a paradigm called 'check-worthiness.' While several studies have examined the accuracy of these algorithms, none have investigated how the benefits from these algorithms (via reduction in exposure to misinformation) are distributed amongst various online communities. In this paper, we investigate how diverse representation across multiple stages of the AI development pipeline affects the distribution of benefits from AI-assisted factchecking for different online communities. We simulate information propagation through the network using our novel Topic-Aware, Community-Impacted Twitter (TACIT) simulator on a large Twitter followers network, tuned to produce realistic cascades of true and false information across multiple topics. Finally, using simulated data as a test bed, we implement numerous algorithmic fact-checking interventions that explicitly account for notions of diversity. We find that both representative and egalitarian methods for sampling and labeling check-worthiness model training data can lead to network-wide benefit concentrated in majority communities, while incorporating diversity into how fact-checkers use algorithmic recommendations can actively reduce inequalities in benefits between majority and minority communities. These findings contribute to an important conversation around the responsible implementation of AI-assisted fact-checking by social media platforms and fact-checking organizations.

show abstract

“…The use of models to analyze and predict the formation of social networks is a large topic of research. Descriptive social network techniques were used in [19] to create new ways to manage crisis de-escalation approaches. The use of social network analysis with respect to engineering and construction project management is evaluated in [20].…”

Section: Practical Problem Setting and Relevant Literaturementioning

confidence: 99%

Robust communication network formation: a decentralized approach

et al. 2019

View full text Add to dashboard Cite

The formation of a communication network is an optimization problem of considerable practical interest. It is the problem of organizing a group decision-making process with a desirable final outcome-a formed network-under a set of constraints that typically include a (hard or soft) limit on communication capacity, or the number of connections that each agent could maintain. A group decision-making process describes (explains) how each agent must behave, i.e., act to build and/or sever communication channels in its own locality. Centralized group decision-making processes, however, are not always adequate for the task at hand, e.g., when dealing with applications related to sensor networks [1], or when Unmanned Aerial Vehicles need to establish and maintain communication, while either not having access to a central hub or preferring not to use this direct transmission channel [2]. Social network formation principles can play a useful role in the modeling of opinion/belief spread en route to achieving the network outcomes. These principles can define how the agents observe their neighbors' actions and local connection structure over time and, based on this information, make better judgments towards what actions could potentially lead to the best global network outcome [3, 4].

show abstract

Social Network Modeling and Agent-Based Simulation in Support of Crisis De-Escalation

Cited by 30 publications

References 27 publications

Network based discrete event analysis for coordination processes in crisis response operations

Network based discrete event analysis for coordination processes in crisis response operations

Does AI-Assisted Fact-Checking Disproportionately Benefit Majority Groups Online?

Robust communication network formation: a decentralized approach

Contact Info

Product

Resources

About