Paper explained
Vandalism or Propaganda? Enhancing Vandalism Detection in Ukrainian and Russian Wikipedia through Knowledge Manipulation Filtering
Can a politically controlled Wikipedia fork reveal subtler forms of manipulation?
The question
Why this work
Obvious vandalism is not the only way to distort an encyclopedia. This symposium paper explores a Russian government-backed Wikipedia fork as a source of signals about narrative changes in Russian and Ukrainian Wikipedia edits.
The approach
A visual guide
Compare content changes with editorial decisions
RWFork
Inspect inserted, removed, and changed text.
Official Wikipedia
Find related revisions and their revert history.
Compare the overlap
Look for recurring shifts in meaning and differences in moderation.
Candidate signals
Use the analysis to guide further manipulation-aware modeling.
What the work contributes
The exploratory analysis found overlapping edits that were accepted in the fork but frequently reverted in official Wikipedia. This supports investigating fork-derived signals as an addition to vandalism detection.
Original paper & resources
6th Masters Symposium on Advances in Data Mining, Machine Learning, and Computer Vision (MS-AMLV 2025), 28–29 March 2025, Lviv, Ukraine.
Citation
Makovska, V., Trokhymovych, M., & Saez-Trumper, D. (2025). Vandalism or Propaganda? Enhancing Vandalism Detection in Ukrainian and Russian Wikipedia through Knowledge Manipulation Filtering. 6th Masters Symposium on Advances in Data Mining, Machine Learning, and Computer Vision (MS-AMLV 2025). https://apps.ucu.edu.ua/wp-content/uploads/2025/07/MS-AMLV-2025-CR-Submission-No-9.pdf
BibTeX
@misc{makovska2025vandalismpropaganda,
title = {Vandalism or Propaganda? Enhancing Vandalism Detection in Ukrainian and Russian Wikipedia through Knowledge Manipulation Filtering},
author = {Makovska, Viktoriia and Trokhymovych, Mykola and Saez-Trumper, Diego},
year = {2025},
note = {MS-AMLV 2025 symposium paper, Ukrainian Catholic University, Lviv},
url = {https://apps.ucu.edu.ua/wp-content/uploads/2025/07/MS-AMLV-2025-CR-Submission-No-9.pdf}
}