--- tags: - bertopic library_name: bertopic pipeline_tag: text-classification --- # bertopic_sim25_10topics_larger_embed_raw This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. ## Usage To use this model, please install BERTopic: ``` pip install -U bertopic ``` You can use the model as follows: ```python from bertopic import BERTopic topic_model = BERTopic.load("DobreMihai/bertopic_sim25_10topics_larger_embed_raw") topic_model.get_topic_info() ``` ## Topic overview * Number of topics: 33 * Number of training documents: 56774
Click here for an overview of all topics. | Topic ID | Topic Keywords | Topic Frequency | Label | |----------|----------------|-----------------|-------| | 0 | app - be - it - this - the | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | android | | 1 | snooze - - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | snooze | | 2 | good - excellent - great - very - ok | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | off | | 3 | nice - update - awesome - the - work | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | update | | 4 | subscription - - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | subscription | | 5 | loud - - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | loud | | 6 | premium - super - be - but - the | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | premium* | | 7 | shake - be - do - the - get | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | shake | | 8 | math - - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | math | | 9 | ad - the - to - be - and | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | ads | | 10 | camera - - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | camera | | 11 | work - it - not - do - help | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | doesn | | 12 | weather - news - the - it - section | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | weather | | 13 | it - the - be - alarm - to | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | -1_it_the_be_alarm | | 14 | the - alarm - not - be - to | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 0_the_alarm_not_be | | 15 | nice - love - very - awesome - excellent | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 1_nice_love_very_awesome | | 16 | very - useful - helpful - easy - work | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 2_very_useful_helpful_easy | | 17 | hai - جدا - من - hi - جميل | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 3_hai_جدا_من_hi | | 18 | be - good - it - amazing - awesome | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 4_be_good_it_amazing | | 19 | experience - good - so - its - it | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 5_experience_good_so_its | | 20 | aap - good - nice - ap - very | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 6_aap_good_nice_ap | | 21 | kumar - nic - exllent - exelent - singh | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 7_kumar_nic_exllent_exelent | | 22 | good - far - so - the - fail | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 8_good_far_so_the | | 23 | gud - goog - gooood - gooooood - blah | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 9_gud_goog_gooood_gooooood | | 24 | que - de - la - para - muy | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 10_que_de_la_para | | 25 | wow - lit - - - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 11_wow_lit__ | | 26 | mission - step - squat - free - count | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 12_mission_step_squat_free | | 27 | не - будильник - это - что - но | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 13_не_будильник_это_что | | 28 | help - lot - alot - tremendously - lottt | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 14_help_lot_alot_tremendously | | 29 | idea - brilliant - amazing - good - great | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 15_idea_brilliant_amazing_good | | 30 | sleeper - heavy - get - up - bed | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 16_sleeper_heavy_get_up | | 31 | ok - its - all - right - guee | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 17_ok_its_all_right | | 32 | ever - well - real - not - | Topic Count 0 0 15865 1 1 10504 5 2 6672 32 13 4076 6 3 3129 15 14 2672 18 15 2291 13 16 1802 7 5 1541 3 4 1541 9 6 821 4 7 786 20 17 666 14 18 650 2 8 539 8 9 450 22 19 449 16 20 371 10 10 369 12 11 368 24 21 206 19 22 195 17 23 193 27 24 160 21 25 110 28 26 106 11 12 61 23 27 44 31 28 34 29 29 33 26 30 31 30 31 28 25 32 11 | 18_ever_well_real_not |
## Training hyperparameters * calculate_probabilities: False * language: None * low_memory: False * min_topic_size: 10 * n_gram_range: (1, 1) * nr_topics: None * seed_topic_list: None * top_n_words: 10 * verbose: False * zeroshot_min_similarity: 0.7 * zeroshot_topic_list: None ## Framework versions * Numpy: 1.26.4 * HDBSCAN: 0.8.38.post1 * UMAP: 0.5.6 * Pandas: 2.2.1 * Scikit-Learn: 1.5.2 * Sentence-transformers: 3.1.0 * Transformers: 4.44.2 * Numba: 0.60.0 * Plotly: 5.24.1 * Python: 3.10.15