Exploiting evolving trust relationships in the modelling of opinion formation dynamics in online social networks
- Authors: Das, Rajkumar , Kamruzzaman, Joarder , Karmakar, Gour
- Date: 2017
- Type: Text , Conference proceedings , Conference paper
- Relation: 31st IEEE International Conference on Advanced Information Networking and Applications, AINA 2017; Taipei, Taiwan; 27th-29th March 2017 p. 872-879
- Full Text: false
- Reviewed:
- Description: 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. © 2017 IEEE.
- Description: Proceedings - International Conference on Advanced Information Networking and Applications, AINA
Who are convincing? An experience based opinion formation dynamics in online social networks
- Authors: Das, Rajkumar , Kamruzzaman, Joarder , Karmakar, Gour
- Date: 2016
- Type: Text , Conference proceedings , Conference paper
- Relation: 30th European Simulation and Modelling Conference, ESM 2016; Las Palmas, Spain; 26th-28th October 2016 p. 167-173
- Full Text: false
- Reviewed:
- Description: Online social network (OSN) is one of the major platforms where our opinions are formed now-a-days and increasing so. Opinion formation dynamics captures the ways public opinions are formed, mainly from two different sources, (i) neighbours' opinions, (ii) external opinions from sources other than the neighbours. In this paper, we formulate an opinion formation model by considering two very important factors, that were ignored or a very little explored in the literature. First, we model the convincing power of the opinions encountered from the two sources. Second, we incorporate the experience of users' previous interactions with the two opinion sources. The problem is formulated as an agent based model where each member of an OSN is represented with an agent and their relationships with a graph. Finally through simulation, we create various scenarios, and apply our model to observe the steady state outcomes of the dynamics. This helps us to study the nature of the public opinions under various influences of our model parameters.
- Description: European Simulation and Modelling Conference 2016, ESM 2016
Consistency driven opinion formation modelling in presence of external sources
- Authors: Das, Rajkumar , Kamruzzaman, Joarder , Karmakar, Gour
- Date: 2015
- Type: Text , Conference proceedings
- Relation: International Joint Conference on Neural Networks, IJCNN 2015; Killarney, Ireland; 12th-17th July 2015
- Full Text: false
- Description: Opinion formation in social networks has changed in a more rigorous way due to the inception of Online Social Networks (OSNs) as a platform of generating and sharing huge amount of contents as well as easy and ubiquitous access to varied information sources. Our opinions are not only updated through interactions with our neighbours in OSNs, but also shaped by the opinions received from information sources external to the native OSNs. Current models only consider the neighbours' influence in opinion evolution, thus lack the impact of other information sources, e.g., news media, web search, bulletin board, discussion forum on opinion formation. They consider individual opinion distances to model the influence among interactive neighbours, but fail to capture the influence of majority supported opinions and its possible impact in opinion evolution. Our model explicitly captures the effect of external sources on opinion formation in an OSN. We combine the implication of most perceived opinions in terms of consistency along with opinion distance to emulate the influence of different opinion sources. Consistency is measured by the entropy of opinions derived from a particular source type. Simulation results show that our model properly captures the consensus, polarization and fragmentation properties of opinion evolution. Finally, we investigate the influence of stubborn agents on opinion formation and compare it with a contemporary model. © 2015 IEEE.
Opinion formation dynamics under the combined influences of majority and experts
- Authors: Das, Rajkumar , Kamruzzaman, Joarder , Karmakar, Gour
- Date: 2015
- Type: Text , Conference proceedings
- Full Text: false
- Description: Opinion formation modelling is still poorly understood due to the hardness and complexity of the abstraction of human behaviours under the presence of various types of social influences. Two such influences that shape the opinion formation process are: (i) the expert effect originated from the presence of experts in a social group and (ii) the majority effect caused by the presence of a large group of people sharing similar opinions. In real life when these two effects contradict each other, they force public opinions towards their respective directions. Existing models employed the concept of confidence levels associated with the opinions to model the expert effect. However, they ignored the majority effect explicitly, and thereby failed to capture the combined impact of these two influences on opinion evolution. Our model explicitly introduces the majority effect through the use of a concept called opinion consistency, and captures the opinion dynamics under the combined influence of majority supported opinions as well as experts’ opinions. Simulation results show that our model properly captures the consensus, polarization and fragmentation properties of public opinion and reveals the impact of the aforementioned effects. © Springer International Publishing Switzerland 2015.