Can Human-Like Bots Control Collective Mood: Agent-Based Simulations of Online Chats

TL;DR

This study uses agent-based simulations to analyze how human-like chat Bots influence collective emotional states in online chats, revealing that Bots can induce and modulate collective emotions and critical-like message avalanches.

Contribution

The paper introduces a quantitative analysis of how emotionally expressive Bots affect collective mood dynamics using fractal analysis and identifies parameters that modulate this influence.

Findings

Positive-emotion Bots are more effective than negative ones.

Emotionally alternating Bots can induce critical-like message avalanches.

Bots can alter the fractal properties of emotional message dynamics.

Abstract

Using agent-based modeling approach, in this paper, we study self-organized dynamics of interacting agents in the presence of chat Bots. Different Bots with tunable ``human-like'' attributes, which exchange emotional messages with agents, are considered, and collective emotional behavior of agents is quantitatively analysed. In particular, using detrended fractal analysis we determine persistent fluctuations and temporal correlations in time series of agent's activity and statistics of avalanches carrying emotional messages of agents when Bots favoring positive/negative affects are active. We determine the impact of Bots and identify parameters that can modulate it. Our analysis suggests that, by these measures, the emotional Bots induce collective emotion among interacting agents by suitably altering the fractal characteristics of the underlying stochastic process.Positive-emotion Bots are slightly more effective than the negative ones. Moreover, the Bots which are periodically alternating between positive and negative emotion, can enhance fluctuations in the system leading to the avalanches of agent's messages that are reminiscent of self-organized critical states.