Detecting bots and assessing their impact in social networks
From MaRDI portal
(Redirected from Publication:5030997)
Abstract: Online social networks are often subject to influence campaigns by malicious actors through the use of automated accounts known as bots. We consider the problem of detecting bots in online social networks and assessing their impact on the opinions of individuals. We begin by analyzing the behavior of bots in social networks and identify that they exhibit heterophily, meaning they interact with humans more than other bots. We use this property to develop a detection algorithm based on the Ising model from statistical physics. The bots are identified by solving a minimum cut problem. We show that this Ising model algorithm can identify bots with higher accuracy while utilizing much less data than other state of the art methods. We then develop a a function we call generalized harmonic influence centrality to estimate the impact bots have on the opinions of users in social networks. This function is based on a generalized opinion dynamics model and captures how the activity level and network connectivity of the bots shift equilibrium opinions. To apply generalized harmonic influence centrality to real social networks, we develop a deep neural network to measure the opinions of users based on their social network posts. Using this neural network, we then calculate the generalized harmonic influence centrality of bots in multiple real social networks. For some networks we find that a limited number of bots can cause non-trivial shifts in the population opinions. In other networks, we find that the bots have little impact. Overall we find that generalized harmonic influence centrality is a useful operational tool to measure the impact of bots in social networks.
Recommendations
- Indirect Causal Influence of a Single Bot on Opinion Dynamics Through a Simple Recommendation Algorithm
- Detecting organization-targeted socialbots by monitoring social network profiles
- Blocking adversarial influence in social networks
- Influence maximization of informed agents in social networks
- Opinion influence and evolution in social networks: a Markovian agents model
Cites work
- A model for spatial conflict
- Automata, Languages and Programming
- Bayesian learning in social networks
- Beitrag zur Theorie des Ferromagnetismus
- Causal Inference Using Potential Outcomes
- Convergence speed in distributed consensus and averaging
- Coordination of groups of mobile autonomous agents using nearest neighbor rules
- Diffusive clustering in the two dimensional voter model
- Distributed asynchronous deterministic and stochastic gradient optimization algorithms
- Duality for general attractive spin systems with applications in one dimension
- Dynamical response of networks under external perturbations: exact results
- Ergodic theorems for weakly interacting infinite systems and the voter model
- scientific article; zbMATH DE number 2062604 (Why is no real title available?)
- Message Passing Optimization of Harmonic Influence Centrality
- On the role of zealotry in the voter model
- Opinion fluctuations and disagreement in social networks
- Reaching a Consensus
- Social and economic networks.
- Towards consensus: some convergence theorems on repeated averaging
- Word-of-mouth learning.
Cited in
(4)- Detecting organization-targeted socialbots by monitoring social network profiles
- Social bot detection as a temporal logic model checking problem
- Dynamic games on arbitrary networks with two types of players
- Formulating opinion dynamics from belief formation, diffusion and updating in social network group decision-making: towards developing a holistic framework
This page was built for publication: Detecting bots and assessing their impact in social networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5030997)
