# Document Clustering on Newsgroup Science Source: [Document Clustering on Newsgroup Science]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:03.068Z Evaluation of unsupervised document clustering performance on the Newsgroup Science dataset, measured using metrics such as Purity and Normalized Mutual Information (NMI). 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 | Document Clustering | | Dataset (including any stated split) | Newsgroup Science | | Metric | Purity | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Purity](): Higher is better; unit: PERCENT. - [NMI](): Higher is better; unit: PERCENT. ## Recorded results | Method | Purity | Result date | Report paper | | --- | --- | --- | --- | | CTM | 73 | Not recorded | 68fa79451e209131cea7cf9e | | DALTA | 57.9 | Not recorded | 68fa79451e209131cea7cf9e | | Meta-CETM | 55.3 | Not recorded | 68fa79451e209131cea7cf9e | | Fastopic | 53.9 | Not recorded | 68fa79451e209131cea7cf9e | | ECRTM | 52.7 | Not recorded | 68fa79451e209131cea7cf9e | | DALTA | 51.3 | Not recorded | 68fa79451e209131cea7cf9e | | LDA | 50 | Not recorded | 68fa79451e209131cea7cf9e | | CTM | 49.5 | Not recorded | 68fa79451e209131cea7cf9e | | ProdLDA | 48.1 | Not recorded | 68fa79451e209131cea7cf9e | | ECRTM | 45.8 | Not recorded | 68fa79451e209131cea7cf9e | | Fastopic | 43.7 | Not recorded | 68fa79451e209131cea7cf9e | | Meta-CETM | 41.5 | Not recorded | 68fa79451e209131cea7cf9e | | ProdLDA | 41.1 | Not recorded | 68fa79451e209131cea7cf9e | | LDA | 41 | Not recorded | 68fa79451e209131cea7cf9e | | ETM | 31.1 | Not recorded | 68fa79451e209131cea7cf9e | | ETM | 30.8 | Not recorded | 68fa79451e209131cea7cf9e | | DeTime | 25.4 | Not recorded | 68fa79451e209131cea7cf9e | | DeTime | 25.4 | Not recorded | 68fa79451e209131cea7cf9e | ### CTM Purity: 73. Result ID: 6995d8673badfaffe6de80b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### DALTA Purity: 57.9. Result ID: 6995d8673badfaffe6de80be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### Meta-CETM Purity: 55.3. Result ID: 6995d8673badfaffe6de80ba. [Reporting paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### Fastopic Purity: 53.9. Result ID: 6995d8673badfaffe6de80bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### ECRTM Purity: 52.7. Result ID: 6995d8673badfaffe6de80b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### DALTA Purity: 51.3. Result ID: 6995d8673badfaffe6de80bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### LDA Purity: 50. Result ID: 6995d8673badfaffe6de80ae. [Reporting paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### CTM Purity: 49.5. Result ID: 6995d8673badfaffe6de80b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### ProdLDA Purity: 48.1. Result ID: 6995d8673badfaffe6de80b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### ECRTM Purity: 45.8. Result ID: 6995d8673badfaffe6de80b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### Fastopic Purity: 43.7. Result ID: 6995d8673badfaffe6de80bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### Meta-CETM Purity: 41.5. Result ID: 6995d8673badfaffe6de80b9. [Reporting paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### ProdLDA Purity: 41.1. Result ID: 6995d8673badfaffe6de80af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### LDA Purity: 41. Result ID: 6995d8673badfaffe6de80ad. [Reporting paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### ETM Purity: 31.1. Result ID: 6995d8673badfaffe6de80b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. ### ETM Purity: 30.8. Result ID: 6995d8673badfaffe6de80b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### DeTime Purity: 25.4. Result ID: 6995d8673badfaffe6de80b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"10"}. This record does not assert independent reproduction. ### DeTime Purity: 25.4. Result ID: 6995d8673badfaffe6de80b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of topics (k)":"20"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.