TrollSleuth: Behavioral and Linguistic Fingerprinting of State-Sponsored Trolls
Bibliographic record
Abstract
Social media has emerged as a key arena for statesponsored disinformation campaigns, where coordinated troll accounts disseminate false narratives and manipulate public discourse. While existing research has primarily focused on detecting such troll accounts, this paper introduces the novel concept of Troll Attribution, drawing on principles from cyber threat attribution. We propose TrollSleuth, a comprehensive framework for attributing troll activity to state sponsors by analyzing linguistic and behavioral fingerprints. Our method integrates four analytical modules-Social Engagement, Word Analysis, Emotion and Sentiment Analysis, and Temporal Activity and Client Utilization Analysis-to extract distinctive features from real-world Twitter data spanning four state-sponsored campaigns. The resulting model achieves a high F1-score of $\mathbf{9 5. 4 8 \%}$ in state-sponsor identification and incorporates featurebased explanations to enhance interpretability. These findings offer actionable insights for strategic intelligence, supporting the detection and deterrence of disinformation operations, informing legal and diplomatic responses, and reinforcing defenses against state-sponsored influence campaigns. The code used in this study is publicly available.11https://github.com/CyberScienceLab/Our-Papers/tree/main/TrollSleuth/
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".