Exploiting Evolving Trust Relationships in the Modelling of Opinion Formation Dynamics in Online Social Networks

Mass participation of the members of a society in discussions to resolve issues related to a topic leads to forming public opinion. The timeline of the underlying dynamics goes through several distinguishable phases, and experiences transition from one to another. After initiated by concerned individuals, it draws active attention from almost everyone, and with time progression, people's participation starts declining as the issues are resolved or lost attraction. The existing works in the literature to capture the opinion formation process pay attention to model the dynamics in its active phase and thus ignore the other phases and the corresponding phase transitions. Trust relationships among the participants dynamically shape their interactions in different stages of the dynamics. Existing works fail to incorporate trust in defining the extent of influence one has on others, as they define the social relationships in the opinion space. To address this issue, we adopt simulated annealing to model the transitional behaviour of the dynamics, and then, amalgamate peoples relationships in the trust space with that in the opinion space to define the meta-heuristics of the algorithm for capturing the dynamical properties of the process. Finally, through simulation, we observe that our model is insightful in representing peoples' evolving behaviour in the different stages of opinion formation process, and consequently, can capture the various properties of the steady-state outcomes of the dynamics.