# Rumor Detection on Telegram Persian Rumor Dataset (test) Source: [Rumor Detection on Telegram Persian Rumor Dataset (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:49.029Z Evaluation of Rumor Detection performance on the test split of the Telegram Persian Rumor Dataset, utilizing precision, recall, and F1 scores across true and false rumor classifications. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Rumor Detection | | Dataset (including any stated split) | Telegram Persian Rumor Dataset (test) | | Metric | Precision (TR) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 3 of 3 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Precision (TR)](): Higher is better; unit: PERCENT. - [Recall (TR)](): Higher is better; unit: PERCENT. - [F1 Score (TR)](): Higher is better; unit: PERCENT. - [Precision (FR)](): Higher is better; unit: PERCENT. - [Recall (FR)](): Higher is better; unit: PERCENT. - [F1 Score (FR)](): Higher is better; unit: PERCENT. - [Precision (Avg)](): Higher is better; unit: PERCENT. - [Recall (Avg)](): Higher is better; unit: PERCENT. - [F1 Score (Avg)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision (TR) | Result date | Report paper | | --- | --- | --- | --- | | Content features + SPR | 85.5 | Not recorded | 68fa6cd91e209131cea36392 | | Jahanbakhsh-Nagadeh et al. | 77.4 | Not recorded | 68fa6cd91e209131cea36392 | | Zamani et al. | 62.8 | Not recorded | 68fa6cd91e209131cea36392 | ### Content features + SPR Precision (TR): 85.5. Result ID: 698f44413a6c314849f7914d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Features":"Content-based + Spread Power of Rumor (SPR)"}. This record does not assert independent reproduction. ### Jahanbakhsh-Nagadeh et al. Precision (TR): 77.4. Result ID: 698f44413a6c314849f7914c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Features":"Content-based"}. This record does not assert independent reproduction. ### Zamani et al. Precision (TR): 62.8. Result ID: 698f44413a6c314849f7914b. [Reporting paper]() Recorded evaluation configuration: {"Features":"Content-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.