Reliability model for inuencing individuals in the social network setting

J. E. Ramirez-Marquez, Ivan Hernandez, Kellie Schneider, Chase Raintwater, Edward A. Pohl

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Social networks have proven to be useful in describing the interactions among individuals in numerous social, professional and military contexts. Recently, researchers have shown increased in- terest in the quantitative study of social networks to determine the most critical members of networks. However, most of the work done at this point is restricted to a binary context (i.e. communication either exists or not among individuals) without any inclusion of reliability considerations. This paper considers a social network in which actors have the ability to provide some level of influence over other actors within the network in a probabilistic manner. The necessary model paradigms to evaluate the influence exchange and propagation in the network are developed. Specifically, the manuscript implements the concept of probabilistic actor influence and influence synergy. A Monte Carlo (MC) simulation model is developed to evaluate and quantify how influence is exchanged and propagated throughout the network. The MC results are then analyzed using two high level performance metrics. Specifically, we consider a general organization level influence model which focuses on analyzing the ex- pected influence level across actors within the network, and also targeted actor influence model which describes the probability of influencing specific network actors (equivalent to 2-terminal reliability). These approaches borrow from and complement theory developed in multi-state network reliability to describe probabilistically the influence of individuals in affecting network outcomes. Finally, we present an illustrative example using both a traditional, centrality-based social network analysis, and the new multi-state influence model with associated performance metrics.

    Original languageEnglish
    Title of host publication11th International Probabilistic Safety Assessment and Management Conference and the Annual European Safety and Reliability Conference 2012, PSAM11 ESREL 2012
    Pages4602-4611
    Number of pages10
    StatePublished - 2012
    Event11th International Probabilistic Safety Assessment and Management Conference and the Annual European Safety and Reliability Conference 2012, PSAM11 ESREL 2012 - Helsinki, Finland
    Duration: 25 Jun 201229 Jun 2012

    Publication series

    Name11th International Probabilistic Safety Assessment and Management Conference and the Annual European Safety and Reliability Conference 2012, PSAM11 ESREL 2012
    Volume6

    Conference

    Conference11th International Probabilistic Safety Assessment and Management Conference and the Annual European Safety and Reliability Conference 2012, PSAM11 ESREL 2012
    Country/TerritoryFinland
    CityHelsinki
    Period25/06/1229/06/12

    Keywords

    • Influence
    • Multi-state
    • Social networks
    • Terminal reliability

    Fingerprint

    Dive into the research topics of 'Reliability model for inuencing individuals in the social network setting'. Together they form a unique fingerprint.

    Cite this