| |
|
| | --- |
| | tags: |
| | - bertopic |
| | library_name: bertopic |
| | pipeline_tag: text-classification |
| | --- |
| | |
| | # MARTINI_enrich_BERTopic_PatAltScotland |
| | |
| | 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("AIDA-UPM/MARTINI_enrich_BERTopic_PatAltScotland") |
| | |
| | topic_model.get_topic_info() |
| | ``` |
| | |
| | ## Topic overview |
| | |
| | * Number of topics: 24 |
| | * Number of training documents: 1834 |
| | |
| | <details> |
| | <summary>Click here for an overview of all topics.</summary> |
| | |
| | | Topic ID | Topic Keywords | Topic Frequency | Label | |
| | |----------|----------------|-----------------|-------| |
| | | -1 | nationalists - edinburgh - british - parliament - snp | 20 | -1_nationalists_edinburgh_british_parliament | |
| | | 0 | refugees - scots - homeless - accommodation - incomers | 799 | 0_refugees_scots_homeless_accommodation | |
| | | 1 | culloden - jacobites - dundee - covenanter - viscount | 92 | 1_culloden_jacobites_dundee_covenanter | |
| | | 2 | leaflets - patrioticalternative - falkirk - active - distributing | 67 | 2_leaflets_patrioticalternative_falkirk_active | |
| | | 3 | activists - workout - stirlingshire - clubs - summit | 61 | 3_activists_workout_stirlingshire_clubs | |
| | | 4 | patalkchannel - live - 7pm - weekly - patriotic | 61 | 4_patalkchannel_live_7pm_weekly | |
| | | 5 | hume - boswell - edinburgh - enlightenment - 1759 | 60 | 5_hume_boswell_edinburgh_enlightenment | |
| | | 6 | crisis - inflation - snp - councils - renewable | 58 | 6_crisis_inflation_snp_councils | |
| | | 7 | scots - edward - berwick - coronation - duncan | 57 | 7_scots_edward_berwick_coronation | |
| | | 8 | pollokshields - murdered - racism - kriss - shahid | 55 | 8_pollokshields_murdered_racism_kriss | |
| | | 9 | lanarkshire - scandal - snp - mackay - councillor | 54 | 9_lanarkshire_scandal_snp_mackay | |
| | | 10 | nhs - understaffed - nurses - ambulance - failures | 53 | 10_nhs_understaffed_nurses_ambulance | |
| | | 11 | transgenderism - rapist - convicted - campaigners - woman | 51 | 11_transgenderism_rapist_convicted_campaigners | |
| | | 12 | linlithgow - decolonise - slaves - banned - councillor | 48 | 12_linlithgow_decolonise_slaves_banned | |
| | | 13 | tudor - darnley - holyrood - mary - crowned | 41 | 13_tudor_darnley_holyrood_mary | |
| | | 14 | lockdown - parliament - authoritarianism - snp - unvaccinated | 38 | 14_lockdown_parliament_authoritarianism_snp | |
| | | 15 | rapist - sentenced - assaulted - offences - murderers | 35 | 15_rapist_sentenced_assaulted_offences | |
| | | 16 | patriotic - articles - alba - gramsci - scoop | 33 | 16_patriotic_articles_alba_gramsci | |
| | | 17 | clydebank - lockerbie - greenock - 1941 - bombs | 32 | 17_clydebank_lockerbie_greenock_1941 | |
| | | 18 | erskinehotelmigrantdemo - protesting - councillors - mcgivern - housed | 29 | 18_erskinehotelmigrantdemo_protesting_councillors_mcgivern | |
| | | 19 | tonight - live - mood - 5pm - thursday | 24 | 19_tonight_live_mood_5pm | |
| | | 20 | racism - bbc - mcavoy - propagandist - mahmood | 24 | 20_racism_bbc_mcavoy_propagandist | |
| | | 21 | patrioticartscommunity - white - august - participate - 2021 | 21 | 21_patrioticartscommunity_white_august_participate | |
| | | 22 | transphobia - schools - sexualised - stonewall - consent | 21 | 22_transphobia_schools_sexualised_stonewall | |
| | |
| | </details> |
| | |
| | ## Training hyperparameters |
| | |
| | * calculate_probabilities: True |
| | * 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: 0.8.40 |
| | * UMAP: 0.5.7 |
| | * Pandas: 2.2.3 |
| | * Scikit-Learn: 1.5.2 |
| | * Sentence-transformers: 3.3.1 |
| | * Transformers: 4.46.3 |
| | * Numba: 0.60.0 |
| | * Plotly: 5.24.1 |
| | * Python: 3.10.12 |
| | |
