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

arXiv: https://arxiv.org/abs/2512.17067 · HTML: https://mlsanity.com/paper/2512.17067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [The Rise of Social Bots](https://mlsanity.com/paper/1407.5225/) (2014)
- [Online Human-Bot Interactions: Detection, Estimation, and Characterization](https://mlsanity.com/paper/1703.03107/) (2017)
- [The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race](https://mlsanity.com/paper/1701.03017/) (2017)
- [Uncovering Coordinated Networks on Social Media: Methods and Case Studies](https://mlsanity.com/paper/2001.05658/) (2020)
- [A Decade of Social Bot Detection](https://mlsanity.com/paper/2007.03604/) (2020)
- [RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter](https://mlsanity.com/paper/1902.04506/) (2019)
- [LOBO -- Evaluation of Generalization Deficiencies in Twitter Bot Classifiers](https://mlsanity.com/paper/1809.09684/) (2018)
- [A Longitudinal Assessment of the Persistence of Twitter Datasets](https://mlsanity.com/paper/1709.09186/) (2017)
- [Dissecting a Social Botnet: Growth, Content and Influence in Twitter](https://mlsanity.com/paper/1604.03627/) (2016)
- [Measuring bot and human behavioral dynamics](https://mlsanity.com/paper/1802.04286/) (2018)
- [Manipulating Twitter Through Deletions](https://mlsanity.com/paper/2203.13893/) (2022)
- [On the efficacy of old features for the detection of new bots](https://mlsanity.com/paper/2506.19635/) (2025)

## Abstract (arXiv)

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.