Sentiment-Based Identification of Radical Authors (SIRA)
Bibliographic record
Abstract
As violent extremists continue to surface in online discussion forums, counter-extremism agencies search for new and innovative ways of uncovering their digital indicators. Using a sample of approximately 1 million posts and 26,000 unique users across four Islamic-based discussion forums, this study proposed a method of identifying the most radical users on the Dark Web. Several characteristics of each user's postings were analyzed using Parts of Speech (POS) tagging, a custom openNLP based tagger, sentiment analysis, and a novel algorithm called "Sentiment-based Identification of Radical Authors" (SIRA). POS tagging was used to develop a list of the 400 most frequently cited nouns across the discussion forums. With this list, sentiment analysis provided the context surrounding users' posts, and each post was assigned a polarity value. Radical scores were calculated using SIRA, which is an algorithm that accounts for a user's percentile score for average sentiment score, volume of negative posts, severity of negative posts, and duration of negative posts. Results did not suggest that a simple typology or typologies best described the most radical users in the Dark Web, however, the findings indicated that SIRA was flexible enough to evaluate several combinations of online activity that could identify the most radical users in the discussion forums. In addition, SIRA identified the same user across two separate discussion forums as the most radical, thus providing validation for the algorithm. This particular user was linked to an extremist website that supported terrorists. Lastly, the results revealed that the Gawaher and Islamic Awakening web forums hosted the highest volume of most radical users in the sample.
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 | 0.000 |
| Science and technology studies | 0.000 | 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".