An explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors

“Social sensors” refer to those who provide opinions through electronic communication channels such as social networks. There are two major issues in current models of sentiment analysis in social sensor networks. First, most existing models only analyzed the sentiment within the text but did not analyze the users, which led to the experimental results difficult to explain. Second, few studies extract the specific opinions of users. Only analyzing the emotional tendencies or aspect-level emotions of social users brings difficulties to the analysis of the opinion evolution in public emergencies. To resolve these issues, we propose an explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors. Our model extracts the specific opinions of the user groups on the topics and fully considers the impacts of their diverse features on sentiment analysis. We conduct experiments on 51,853 tweets about the “COVID-19” collected from 1 May 2020 to 9 July 2020. We build users’ portraits from three aspects: attribute features, interest features, and emotional features. Six machine learning algorithms are used to predict emotional tendency based on users’ portraits. We analyze the influence of users’ features on the sentiment. The prediction accuracy of our model is 64.88%.

Opinion evolution in society with stubborn agents using Temporal Model for Opinion and Triad Network Formation (TMOTNF)

Information diffusion is an important part of the social network. Information flows between the individuals in the social networks to shape and update their opinions about various topics. The updated opinion values of them further spread the information in the network. The social network is always evolving by nature, leading to the dynamics of the network. Connections keep on changing among the individuals based on the various characteristics of the networks and individuals. Opinions of individuals may again be affected by the changes in the network which leads to dynamics on the network. Therefore, the co-evolving nature of dynamics on/of the network is proposed. Co-evolving Temporal Model for Opinion and Triad Network Formation is modelled to evaluate the opinion convergence. Some fully stubborn agents are chosen in the network to affect opinion evolution, framing society’s opinion. It is also analysed how these agents can divert the whole network towards their opinion values. When temporal modelling is done using all the three conditions, Triadic Closure, Opinion Threshold value and the Page Rank value over the network, the network does not reach consensus at the convergence point. Various individuals with different opinion values still exist.

Group Polarization Based on Agent Emotional Characteristics and Credibility

The frequent occurrence of group polarization in many internet mass incidents produces adverse impacts on the social stability and poses a significant challenge for social management. We construct an opinion evolution model with agent emotional characteristics and credibility based on the Deffuant model to study the evolutionary mechanism of group polarization, which connects the agent’s firmness with the agent’s opinion, taking a full account of the agent heterogeneity. We analyze the impacts of initial opinion distribution, network structure, and opinion leader on the group opinion evolution. The results show that group polarization is easier to form when the initial opinions are in a normal distribution, and group polarization will also form under the impact of initial minority agents with extreme opinions. Different network structures will pose different effects on the group opinion evolution, and group polarization is easier to form in the small-world network and BA scale-free network. In addition, opinion leader also affects the group opinion evolution, and it will hinder the generation of group polarization.

The Analysis of Opinion Evolution and Control Based on the Prisoner’s Dilemma Game in Social Networks

In a social network, a user is greatly influenced by their neighbors’ opinions, and the user’s opinion updating can be regarded as the prisoner’s dilemma game. In view of such considerations, this paper proposes an opinion evolution and control model based on the prisoner’s dilemma game and gives the corresponding opinion evolution and control algorithm. Under different initial positive opinion proportions, different opinion control levels, and the same control threshold value and under different initial positive opinion proportions, different opinion control levels, and different opinion control threshold values in a scale-free network, the experiments illustrate the opinion evolution trends and control strategies according to the measures of changing the opinion control levels and opinion control threshold values for network regulators. The experiments show that the lower the initial positive opinion proportion is and the smaller (resp., larger) the control opinion threshold value chosen by the network regulators is, the lower (resp., higher) the opinion control level is; the larger the initial positive opinion proportion is and the larger the control opinion threshold value chosen by the network regulators is, the lower the opinion control level is.