Investigation of machine learning approaches to classify war-related content during Russian full-scale invasion of Ukraine
Bibliographic record
Abstract
Social media platforms are digital arenas for information dissemination. Consequently, they have become a battlefront for disinformation, propaganda, fake news, and strategic narratives during emerging geopolitical events such as war. Machine learning has increasingly been developed to systematically analyze and classify digital content, shedding light on online propaganda’s underlying patterns and strategies. Here we applied multiple machine learning algorithms to classify pro-Russian communications on Twitter (tweets) following the Russian full-scale invasion of Ukraine. Machine learning models included Logistic Regression, Support Vector Machine, Bi-directional Long Short Term Memory, Naive Bayes, K-Nearest Neighbours, and Extreme Gradient Boosting. Model performances were evaluated based on accuracy, precision, recall, and F1-score metrics. The Support Vector Machine and Extreme Gradient Boosting models consistently outperformed others, achieving higher accuracy and F1 scores. In general, model performance improved with increasing dataset size. The results highlighted the complexities of online informational manipulation, emphasizing the need for a deeper sentiment analysis. This study offers a pioneering contribution to understanding information manipulation in the context of the Russia-Ukraine war and provides valuable insights into the intricacies of digital information warfare.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".