bertopic_ver2.0 / README.md
hts98's picture
Add BERTopic model
6a3a6ee
---
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
---
# bertopic_ver2.0
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("hts98/bertopic_ver2.0")
topic_model.get_topic_info()
```
## Topic overview
* Number of topics: 207
* Number of training documents: 529579
<details>
<summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|----------|----------------|-----------------|-------|
| -1 | ok - ms - wifi - swimming - balcony | 150 | -1_ok_ms_wifi_swimming |
| 0 | hanoi - quarter - halong - sapa - lake | 217212 | 0_hanoi_quarter_halong_sapa |
| 1 | vietnamese - vietnam - viet - western - weeks | 47397 | 1_vietnamese_vietnam_viet_western |
| 2 | hoi - homestay - ancient - bikes - bicycles | 46092 | 2_hoi_homestay_ancient_bikes |
| 3 | told - smell - said - dirty - com | 16583 | 3_told_smell_said_dirty |
| 4 | hostel - dorm - dorms - hostels - lockers | 12960 | 4_hostel_dorm_dorms_hostels |
| 5 | saigon - square - ben - district - thanh | 12475 | 5_saigon_square_ben_district |
| 6 | bikes - bike - bicycles - rent - scooter | 8246 | 6_bikes_bike_bicycles_rent |
| 7 | minh - ho - chi - district - city | 6633 | 7_minh_ho_chi_district |
| 8 | hue - citadel - perfume - imperial - tombs | 6057 | 8_hue_citadel_perfume_imperial |
| 9 | noise - loud - noisy - music - hear | 4572 | 9_noise_loud_noisy_music |
| 10 | villa - villas - bedroom - private - butler | 4060 | 10_villa_villas_bedroom_private |
| 11 | sea - ocean - beach - seaview - khe | 4032 | 11_sea_ocean_beach_seaview |
| 12 | nha - trang - nhi - novotel - nhatrang | 3936 | 12_nha_trang_nhi_novotel |
| 13 | hcmc - district - ben - rooftop - attractions | 3890 | 13_hcmc_district_ben_rooftop |
| 14 | massage - spa - therapist - massages - body | 3680 | 14_massage_spa_therapist_massages |
| 15 | swimming - pool - roof - rooftop - swim | 3645 | 15_swimming_pool_roof_rooftop |
| 16 | resort - resorts - pools - grounds - relaxing | 3495 | 16_resort_resorts_pools_grounds |
| 17 | quarter - quarters - old - heart - middle | 3454 | 17_quarter_quarters_old_heart |
| 18 | nang - da - khe - han - fivitel | 3311 | 18_nang_da_khe_han |
| 19 | staffs - polite - helped - desk - kind | 2991 | 19_staffs_polite_helped_desk |
| 20 | hostel - hostels - backpackers - dorm - tomodachi | 2813 | 20_hostel_hostels_backpackers_dorm |
| 21 | mekong - delta - floating - lodge - tho | 2779 | 21_mekong_delta_floating_lodge |
| 22 | hostel - hostels - dalat - dorm - dorms | 2694 | 22_hostel_hostels_dalat_dorm |
| 23 | center - shopping - centre - city - attractions | 2650 | 23_center_shopping_centre_city |
| 24 | longer - nights - stayed - enjoyed - total | 2465 | 24_longer_nights_stayed_enjoyed |
| 25 | halong - cruise - bay - cruises - overnight | 2380 | 25_halong_cruise_bay_cruises |
| 26 | danang - sanouva - han - dragon - khe | 2346 | 26_danang_sanouva_han_dragon |
| 27 | quoc - phu - island - regent - bauhinia | 2314 | 27_quoc_phu_island_regent |
| 28 | asia - chinese - se - hong - asian | 2298 | 28_asia_chinese_se_hong |
| 29 | ben - thanh - halal - muslim - market | 2268 | 29_ben_thanh_halal_muslim |
| 30 | lake - west - quarter - cathedral - sword | 2114 | 30_lake_west_quarter_cathedral |
| 31 | nights - 2015 - 2018 - stayed - november | 2068 | 31_nights_2015_2018_stayed |
| 32 | kiem - hoan - lake - hoam - joseph | 2036 | 32_kiem_hoan_lake_hoam |
| 33 | swimming - pools - pool - swim - kids | 2017 | 33_swimming_pools_pool_swim |
| 34 | siesta - la - trendy - bean - premium | 1958 | 34_siesta_la_trendy_bean |
| 35 | river - riverview - overlooking - views - boat | 1841 | 35_river_riverview_overlooking_views |
| 36 | star - stars - rating - 5star - rated | 1829 | 36_star_stars_rating_5star |
| 37 | phong - nha - farmstay - cave - caves | 1760 | 37_phong_nha_farmstay_cave |
| 38 | lounge - club - executive - platinum - accor | 1671 | 38_lounge_club_executive_platinum |
| 39 | ninh - binh - coc - mua - vancouver | 1657 | 39_ninh_binh_coc_mua |
| 40 | birthday - cake - honeymoon - wedding - anniversary | 1581 | 40_birthday_cake_honeymoon_wedding |
| 41 | market - convenient - shopping - markets - center | 1562 | 41_market_convenient_shopping_markets |
| 42 | mui - ne - hills - muine - thiet | 1392 | 42_mui_ne_hills_muine |
| 43 | sapa - train - halong - bay - trips | 1389 | 43_sapa_train_halong_bay |
| 44 | hcm - district - ben - hcmh - thanh | 1376 | 44_hcm_district_ben_hcmh |
| 45 | district - d1 - attractions - rooftop - heart | 1334 | 45_district_d1_attractions_rooftop |
| 46 | lodge - bamboo - tien - cottages - national | 1314 | 46_lodge_bamboo_tien_cottages |
| 47 | villa - villas - hoi - cherry - tnt | 1232 | 47_villa_villas_hoi_cherry |
| 48 | speak - english - speaks - spoke - language | 1151 | 48_speak_english_speaks_spoke |
| 49 | ha - bay - long - cruise - boat | 1143 | 49_ha_bay_long_cruise |
| 50 | hue - citadel - serene - imperial - perfume | 1130 | 50_hue_citadel_serene_imperial |
| 51 | cat - ba - catba - island - woodstock | 1121 | 51_cat_ba_catba_island |
| 52 | japanese - yen - japan - bridge - tokyo | 1099 | 52_japanese_yen_japan_bridge |
| 53 | siesta - la - trendy - premium - bean | 1038 | 53_siesta_la_trendy_premium |
| 54 | airport - transit - taxi - flight - uber | 1020 | 54_airport_transit_taxi_flight |
| 55 | tau - vung - pullman - malibu - mercure | 1010 | 55_tau_vung_pullman_malibu |
| 56 | loop - giang - bong - guides - ha | 979 | 56_loop_giang_bong_guides |
| 57 | dalat - edensee - valley - golf - center | 927 | 57_dalat_edensee_valley_golf |
| 58 | anantara - ne - mui - noel - anantaras | 857 | 58_anantara_ne_mui_noel |
| 59 | naman - retreat - ambassador - hay - babylon | 841 | 59_naman_retreat_ambassador_hay |
| 60 | beach - 40km - sea - chill - sand | 769 | 60_beach_40km_sea_chill |
| 61 | vinpearl - vin - safari - pearl - discovery | 749 | 61_vinpearl_vin_safari_pearl |
| 62 | vegan - vegetarian - vegetarians - seafood - chicken | 715 | 62_vegan_vegetarian_vegetarians_seafood |
| 63 | salinda - quoc - phu - jeevan - indian | 702 | 63_salinda_quoc_phu_jeevan |
| 64 | dao - senses - condor - poulo - van | 695 | 64_dao_senses_condor_poulo |
| 65 | french - colonial - france - paris - style | 689 | 65_french_colonial_france_paris |
| 66 | thank - ms - appreciation - smile - express | 688 | 66_thank_ms_appreciation_smile |
| 67 | dragon - han - bridge - rising - river | 686 | 67_dragon_han_bridge_rising |
| 68 | james - basic - helpfull - slave - supporting | 683 | 68_james_basic_helpfull_slave |
| 69 | noi - ha - graceful - hoan - kiem | 657 | 69_noi_ha_graceful_hoan |
| 70 | host - hosts - hostal - hostess - family | 629 | 70_host_hosts_hostal_hostess |
| 71 | metropole - sofitel - wing - legend - history | 623 | 71_metropole_sofitel_wing_legend |
| 72 | coc - tam - mua - caves - ecolodge | 617 | 72_coc_tam_mua_caves |
| 73 | opera - wing - house - hilton - history | 599 | 73_opera_wing_house_hilton |
| 74 | citadel - tombs - perfume - imperial - pagoda | 581 | 74_citadel_tombs_perfume_imperial |
| 75 | residencia - la - residence - dora - casa | 558 | 75_residencia_la_residence_dora |
| 76 | pros - cons - pro - poor - properly | 540 | 76_pros_cons_pro_poor |
| 77 | fusion - fusionista - treatments - quoc - phu | 526 | 77_fusion_fusionista_treatments_quoc |
| 78 | mia - sandals - cliff - baia - cindy | 502 | 78_mia_sandals_cliff_baia |
| 79 | kiman - kim - mama - kims - ty | 490 | 79_kiman_kim_mama_kims |
| 80 | ming - ho - min - chi - mihn | 487 | 80_ming_ho_min_chi |
| 81 | oriental - suites - mary - central - brian | 483 | 81_oriental_suites_mary_central |
| 82 | rex - follies - governor - history - journalists | 475 | 82_rex_follies_governor_history |
| 83 | veranda - la - quoc - phu - colonial | 467 | 83_veranda_la_quoc_phu |
| 84 | island - bungalows - bungalow - beaches - snorkeling | 458 | 84_island_bungalows_bungalow_beaches |
| 85 | mango - eco - plantation - bay - bungalow | 450 | 85_mango_eco_plantation_bay |
| 86 | lat - da - dreams - axel - amore | 442 | 86_lat_da_dreams_axel |
| 87 | ancient - town - tai - shuttle - bicycle | 442 | 87_ancient_town_tai_shuttle |
| 88 | nha - trang - russian - anam - regalia | 436 | 88_nha_trang_russian_anam |
| 89 | chau - mai - valley - ecolodge - villages | 435 | 89_chau_mai_valley_ecolodge |
| 90 | hyatt - park - saigon - opera - square | 424 | 90_hyatt_park_saigon_opera |
| 91 | serene - shining - palace - hue - premier | 421 | 91_serene_shining_palace_hue |
| 92 | dong - geminai - khoi - myst - caves | 410 | 92_dong_geminai_khoi_myst |
| 93 | hcmc - district - anpha - chahn - vietnam | 406 | 93_hcmc_district_anpha_chahn |
| 94 | jw - marriott - executive - lounge - grill | 403 | 94_jw_marriott_executive_lounge |
| 95 | silverland - jolie - sakyo - yen - afternoon | 403 | 95_silverland_jolie_sakyo_yen |
| 96 | korean - korea - koreans - ri - chung | 399 | 96_korean_korea_koreans_ri |
| 97 | notre - dame - war - museum - remnants | 396 | 97_notre_dame_war_museum |
| 98 | golden - moon - legend - alisa - jay | 395 | 98_golden_moon_legend_alisa |
| 99 | selva - la - jackie - kevin - jane | 395 | 99_selva_la_jackie_kevin |
| 100 | palm - garden - gardens - palmy - resort | 395 | 100_palm_garden_gardens_palmy |
| 101 | nang - da - chicland - dragon - buddha | 394 | 101_nang_da_chicland_dragon |
| 102 | saigon - hostel - hideout - dorm - backpackers | 389 | 102_saigon_hostel_hideout_dorm |
| 103 | golden - sun - suites - eric - jessie | 386 | 103_golden_sun_suites_eric |
| 104 | cambodia - border - cambodian - penh - phnom | 384 | 104_cambodia_border_cambodian_penh |
| 105 | metropole - sofitel - wing - legend - history | 382 | 105_metropole_sofitel_wing_legend |
| 106 | ngu - lao - pham - vien - bui | 372 | 106_ngu_lao_pham_vien |
| 107 | town - old - obsequious - storeplace - 75us | 363 | 107_town_old_obsequious_storeplace |
| 108 | moon - alisa - bob - madam - lunar | 362 | 108_moon_alisa_bob_madam |
| 109 | nhon - quy - avani - flc - seagull | 354 | 109_nhon_quy_avani_flc |
| 110 | riverside - royal - na - tham - river | 352 | 110_riverside_royal_na_tham |
| 111 | oriental - suites - mary - central - brian | 344 | 111_oriental_suites_mary_central |
| 112 | jade - hue - scene - citadel - juice | 334 | 112_jade_hue_scene_citadel |
| 113 | alagon - maison - ma - antique - dantique | 333 | 113_alagon_maison_ma_antique |
| 114 | minh - ho - chi - hostel - dablend | 329 | 114_minh_ho_chi_hostel |
| 115 | christina - christinas - trevor - mothership - onetrip | 327 | 115_christina_christinas_trevor_mothership |
| 116 | lotus - royal - chin - veronica - danang | 327 | 116_lotus_royal_chin_veronica |
| 117 | wifi - signal - fi - wi - internet | 324 | 117_wifi_signal_fi_wi |
| 118 | russian - russians - russia - volga - moscow | 319 | 118_russian_russians_russia_volga |
| 119 | liberty - citypoint - riverside - central - saigon | 312 | 119_liberty_citypoint_riverside_central |
| 120 | hcmc - saigon - square - zohn - district | 309 | 120_hcmc_saigon_square_zohn |
| 121 | marriott - jw - marriotts - platinum - elite | 302 | 121_marriott_jw_marriotts_platinum |
| 122 | essence - palace - suzy - christine - phoebe | 301 | 122_essence_palace_suzy_christine |
| 123 | gym - fitness - equipment - weights - machines | 298 | 123_gym_fitness_equipment_weights |
| 124 | hai - phong - somerset - avani - td | 297 | 124_hai_phong_somerset_avani |
| 125 | window - windows - windowless - claustrophobic - corridor | 297 | 125_window_windows_windowless_claustrophobic |
| 126 | lotte - dennis - dat - 63 - department | 296 | 126_lotte_dennis_dat_63 |
| 127 | orchid - orchids - tammy - garden - hue | 289 | 127_orchid_orchids_tammy_garden |
| 128 | pullman - accor - saigon - executive - cow | 288 | 128_pullman_accor_saigon_executive |
| 129 | golden - sun - suites - eric - palace | 282 | 129_golden_sun_suites_eric |
| 130 | moon - luna - moons - tri - tailoring | 281 | 130_moon_luna_moons_tri |
| 131 | bartender - rooftop - cocktails - bar - cocktail | 280 | 131_bartender_rooftop_cocktails_bar |
| 132 | maia - fusion - treatments - fusionista - spa | 267 | 132_maia_fusion_treatments_fusionista |
| 133 | peppercorn - pepper - farm - brewery - kayaks | 267 | 133_peppercorn_pepper_farm_brewery |
| 134 | amiana - pools - mud - nha - trang | 265 | 134_amiana_pools_mud_nha |
| 135 | dalat - canyoning - hostel - luu - dinner | 255 | 135_dalat_canyoning_hostel_luu |
| 136 | english - speak - speaks - spoke - speaking | 254 | 136_english_speak_speaks_spoke |
| 137 | rosaleen - rosaka - nhi - rosa - rosabella | 254 | 137_rosaleen_rosaka_nhi_rosa |
| 138 | boutique - pama - della - charming - definition | 254 | 138_boutique_pama_della_charming |
| 139 | pullman - accor - cow - quoc - mad | 254 | 139_pullman_accor_cow_quoc |
| 140 | hoian - rossie - ancient - hoians - ahoy | 252 | 140_hoian_rossie_ancient_hoians |
| 141 | nikko - saigon - japanese - seafood - club | 252 | 141_nikko_saigon_japanese_seafood |
| 142 | apricot - artwork - chandeliers - sketch - lake | 245 | 142_apricot_artwork_chandeliers_sketch |
| 143 | sofia - antonio - nang - ryan - danang | 244 | 143_sofia_antonio_nang_ryan |
| 144 | gia - pham - thy - nga - homestay | 244 | 144_gia_pham_thy_nga |
| 145 | song - lam - villa - saigon - speedboat | 242 | 145_song_lam_villa_saigon |
| 146 | indochine - palace - hue - bwp - christine | 242 | 146_indochine_palace_hue_bwp |
| 147 | anam - pools - eka - ranh - cam | 241 | 147_anam_pools_eka_ranh |
| 148 | rooftop - roof - bar - barrestaurant - sky | 239 | 148_rooftop_roof_bar_barrestaurant |
| 149 | hoang - trinh - tan - le - madam | 236 | 149_hoang_trinh_tan_le |
| 150 | golden - legend - gold - diamond - art | 236 | 150_golden_legend_gold_diamond |
| 151 | jacuzzi - sauna - jacuzzis - steam - afternoon | 235 | 151_jacuzzi_sauna_jacuzzis_steam |
| 152 | sheraton - sheratons - spg - briana - tran | 233 | 152_sheraton_sheratons_spg_briana |
| 153 | thai - bangkok - thailand - bao - und | 226 | 153_thai_bangkok_thailand_bao |
| 154 | muca - osaka - gardens - vegetable - riverside | 226 | 154_muca_osaka_gardens_vegetable |
| 155 | sheraton - nha - trang - altitude - briana | 225 | 155_sheraton_nha_trang_altitude |
| 156 | vien - bui - bu - street - alley | 224 | 156_vien_bui_bu_street |
| 157 | ruby - pearl - sapphire - amber - thien | 223 | 157_ruby_pearl_sapphire_amber |
| 158 | australia - australian - aussie - melbourne - australians | 222 | 158_australia_australian_aussie_melbourne |
| 159 | sherwood - residence - suites - apartment - dryer | 221 | 159_sherwood_residence_suites_apartment |
| 160 | selva - la - sinfonia - vela - del | 219 | 160_selva_la_sinfonia_vela |
| 161 | hyatt - park - globalist - dreyer - agathe | 219 | 161_hyatt_park_globalist_dreyer |
| 162 | hai - nam - seasons - butler - ghm | 217 | 162_hai_nam_seasons_butler |
| 163 | liberty - citypoint - central - riverside - bistro | 216 | 163_liberty_citypoint_central_riverside |
| 164 | 3b - homestay - bc - hanowood - luan | 213 | 164_3b_homestay_bc_hanowood |
| 165 | vinh - hung - emerald - riverside - library | 213 | 165_vinh_hung_emerald_riverside |
| 166 | buffet - restau - extensive - buffets - ladyship | 213 | 166_buffet_restau_extensive_buffets |
| 167 | jm - marvel - cuong - anna - lucy | 210 | 167_jm_marvel_cuong_anna |
| 168 | write - review - reviews - advisor - compelled | 207 | 168_write_review_reviews_advisor |
| 169 | meridien - le - spg - saigon - andy | 206 | 169_meridien_le_spg_saigon |
| 170 | heaven - green - phuoc - tuong - thuy | 205 | 170_heaven_green_phuoc_tuong |
| 171 | gallery - premier - majestic - brian - monica | 205 | 171_gallery_premier_majestic_brian |
| 172 | hano - hanio - hani - hannoi - recommand | 203 | 172_hano_hanio_hani_hannoi |
| 173 | nikko - japanese - club - okura - beige | 201 | 173_nikko_japanese_club_okura |
| 174 | 1010 - 910 - tak - humbleness - 810 | 201 | 174_1010_910_tak_humbleness |
| 175 | imperial - palace - tombs - perfume - falicities | 201 | 175_imperial_palace_tombs_perfume |
| 176 | pearl - junie - amanda - betty - dominic | 194 | 176_pearl_junie_amanda_betty |
| 177 | siesta - la - lavita - trendy - bean | 192 | 177_siesta_la_lavita_trendy |
| 178 | leo - tigers - tiger - tiny - canyoning | 191 | 178_leo_tigers_tiger_tiny |
| 179 | omelette - omelettes - omelet - omelets - vissai | 190 | 179_omelette_omelettes_omelet_omelets |
| 180 | lat - da - canyoning - hostel - dablend | 188 | 180_lat_da_canyoning_hostel |
| 181 | melia - meli - vi - mellia - bavi | 186 | 181_melia_meli_vi_mellia |
| 182 | muong - thanh - tinh - quang - mung | 182 | 182_muong_thanh_tinh_quang |
| 183 | grand - hmc - tower - wing - hotram | 181 | 183_grand_hmc_tower_wing |
| 184 | tho - kieu - xoai - quay - floating | 180 | 184_tho_kieu_xoai_quay |
| 185 | infinity - suresh - ocean - 47th - ying | 180 | 185_infinity_suresh_ocean_47th |
| 186 | lasenta - fields - rice - paddy - infinity | 180 | 186_lasenta_fields_rice_paddy |
| 187 | cherish - hue - larry - citadel - jay | 179 | 187_cherish_hue_larry_citadel |
| 188 | venus - tracey - sunny - uyen - tick | 178 | 188_venus_tracey_sunny_uyen |
| 189 | bonsella - prestige - jason - eddie - kiem | 176 | 189_bonsella_prestige_jason_eddie |
| 190 | pilgrimage - village - miwa - slope - pilgrim | 175 | 190_pilgrimage_village_miwa_slope |
| 191 | alba - wellness - onsen - springs - zipline | 174 | 191_alba_wellness_onsen_springs |
| 192 | sheraton - towers - tower - saigon - lounge | 172 | 192_sheraton_towers_tower_saigon |
| 193 | somerset - chancellor - apartment - apartments - court | 172 | 193_somerset_chancellor_apartment_apartments |
| 194 | essence - palace - tom - suzy - christine | 170 | 194_essence_palace_tom_suzy |
| 195 | royal - palace - prince - expierence - citybay | 170 | 195_royal_palace_prince_expierence |
| 196 | bungalow - bungalows - beach - beachfront - seaside | 168 | 196_bungalow_bungalows_beach_beachfront |
| 197 | sofitel - plaza - saigon - mezz - club | 166 | 197_sofitel_plaza_saigon_mezz |
| 198 | maison - vy - privileges - cargo - glory | 165 | 198_maison_vy_privileges_cargo |
| 199 | deluxe - superior - premium - amex - standard | 163 | 199_deluxe_superior_premium_amex |
| 200 | melia - vi - bavi - ba - mountain | 160 | 200_melia_vi_bavi_ba |
| 201 | emerald - waters - elegance - jasmine - trendy | 157 | 201_emerald_waters_elegance_jasmine |
| 202 | mosquitoes - mosquito - mosquitos - repellent - nets | 155 | 202_mosquitoes_mosquito_mosquitos_repellent |
| 203 | storia - ruby - la - isabella - jasmine | 153 | 203_storia_ruby_la_isabella |
| 204 | gallery - ogallery - premier - majestic - thomas | 152 | 204_gallery_ogallery_premier_majestic |
| 205 | jw - marriott - university - lamarck - quoc | 151 | 205_jw_marriott_university_lamarck |
</details>
## 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: True
* zeroshot_min_similarity: 0.7
* zeroshot_topic_list: None
## Framework versions
* Numpy: 1.24.3
* HDBSCAN: 0.8.33
* UMAP: 0.5.5
* Pandas: 2.0.3
* Scikit-Learn: 1.2.2
* Sentence-transformers: 2.2.2
* Transformers: 4.35.2
* Numba: 0.57.1
* Plotly: 5.16.1
* Python: 3.10.12