Big data-drive agent-based modeling of online polarized opinions

Peng Lu,Zhuo Zhang,Mengdi Li

doi:10.1007/s40747-021-00532-5

Peng Lu, Zhuo Zhang + Show 1 more

Open Access

https://doi.org/10.1007/s40747-021-00532-5

Copy DOI

Abstract

Under the mobile internet and big data era, more and more people are discussing and interacting online with each other. The forming process and evolutionary dynamics of public opinions online have been heavily investigated. Using agent-based modeling, we expand the Ising model to explore how individuals behave and the evolutionary mechanism of the life cycles. The big data platform of Douban.com is selected as the data source, and the online case “NeiYuanWaiFang” is applied as the real target, for our modeling and simulations to match. We run 10,000 simulations to find possible optimal solutions, and we run 10,000 times again to check the robustness and adaptability. The optimal solution simulations can reflect the whole life cycle process. In terms of different levels and indicators, the fitting or matching degrees achieve the highest levels. At the micro-level, the distributions of individual behaviors under real case and simulations are similar to each other, and they all follow normal distributions; at the middle-level, both discrete and continuous distributions of supportive and oppositive online comments are matched between real case and simulations; at the macro-level, the life cycle process (outbreak, rising, peak, and vanish) and durations can be well matched. Therefore, our model has properly seized the core mechanism of individual behaviors, and precisely simulated the evolutionary dynamics of online cases in reality.

Highlights

With the rapid development of Information and Communications Technologies (ICTs), more and more people are using internet to express opinions and exchange information [1]
The disappearance and change of individual viewpoint will not destroy the whole information network, which greatly avoids the vulnerability of scale-free network [47]; and (c) Ising model is good at modeling shifting and extreme viewpoints of individuals
We model the dynamics of opinion-forming, using agent-based model and simulations

Summary

Introduction

With the rapid development of Information and Communications Technologies (ICTs), more and more people are using internet to express opinions and exchange information [1]. The disappearance and change of individual viewpoint will not destroy the whole information network, which greatly avoids the vulnerability of scale-free network [47]; and (c) Ising model is good at modeling shifting and extreme viewpoints of individuals For this case, viewpoints of many people online change relatively quickly and emotionally, and, in Douban.com, a tiny change of information may cause reversals of entire public opinions. We combine multiple methods, such as real case analysis, big data mining, agent-based modeling, and simulations. Knowledge-discovery in databases (KDD), rough the same as big data mining, refers to the capability of extracting useful information from large datasets [54] It uncovers complex patterns of hidden relationships, within large-scale data, and facilitates valuable predictions based on real-world observations. We calculate sentiment values by uploading the captured text and using the sentiment analysis

Discussion

Findings

Conclusions and discussion