Bots Don't Sit Still: A Longitudinal Study of Bot Behaviour Change, Temporal Drift, and Feature-Structure Evolution

2025-12-18

AI Summary

This study investigates the temporal stationarity of social bot behavioral characteristics and its implications for bot detection system efficacy. Method: Leveraging a decade-long longitudinal dataset comprising 2,615 promotional Twitter bots and 2.8 million tweets, we apply ADF/KPSS stationarity tests, Spearman correlation, chi-square tests, and hierarchical time-series modeling to construct an interpretable 18-dimensional behavioral feature space and 153 co-occurrence relationships. Contribution/Results: All ten content-level meta-features exhibit statistically significant non-stationarity—nine increase over time, while linguistic diversity slightly declines. Bot generation cohort and survival duration emerge as critical moderating variables. Later-generation bots display increasingly structured, multimodal, and coordinated behavioral patterns. This work establishes the first empirical foundation for dynamic bot detection, providing both theoretical insights into bot evolution and a novel, interpretable temporal modeling framework for adaptive detection systems.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Social bots are now deeply embedded in online platforms for promotion, persuasion, and manipulation. Most bot-detection systems still treat behavioural features as static, implicitly assuming bots behave stationarily over time. We test that assumption for promotional Twitter bots, analysing change in both individual behavioural signals and the relationships between them. Using 2,615 promotional bot accounts and 2.8M tweets, we build yearly time series for ten content-based meta-features. Augmented Dickey-Fuller and KPSS tests plus linear trends show all ten are non-stationary: nine increase over time, while language diversity declines slightly. Stratifying by activation generation and account age reveals systematic differences: second-generation bots are most active and link-heavy; short-lived bots show intense, repetitive activity with heavy hashtag/URL use; long-lived bots are less active but more linguistically diverse and use emojis more variably. We then analyse co-occurrence across generations using 18 interpretable binary features spanning actions, topic similarity, URLs, hashtags, sentiment, emojis, and media (153 pairs). Chi-square tests indicate almost all pairs are dependent. Spearman correlations shift in strength and sometimes polarity: many links (e.g. multiple hashtags with media; sentiment with URLs) strengthen, while others flip from weakly positive to weakly or moderately negative. Later generations show more structured combinations of cues. Taken together, these studies provide evidence that promotional social bots adapt over time at both the level of individual meta-features and the level of feature interdependencies, with direct implications for the design and evaluation of bot-detection systems trained on historical behavioural features.

Problem

• Analyzes how promotional social bots evolve behaviorally over time.
• Examines changes in individual bot features and their interdependencies.
• Highlights implications for bot-detection systems using historical data.

Innovation

• Analyzing bot behavior changes over time with statistical tests
• Identifying systematic differences across bot generations and lifespans
• Revealing evolving feature interdependencies impacting detection systems