%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Chat Topics
基于BERTopic的聊天话题分类模型，能够从海量文本数据中自动识别和分类话题
Downloads 262
Release Time : 5/29/2023
Model Overview
该模型使用BERTopic框架构建，专门用于分析聊天文本并提取有意义的话题分类。适用于社交媒体、客服对话等场景的话题挖掘和分析。
Model Features
模块化设计
采用BERTopic的模块化框架，可灵活调整各个处理环节
多话题识别
能够自动识别75个不同的话题类别
关键词提取
为每个话题提供最具代表性的关键词
大规模训练
基于63,530篇文档训练，覆盖广泛话题
Model Capabilities
文本分类
话题识别
关键词提取
话题可视化
Use Cases
社交媒体分析
聊天话题监控
分析社交媒体上的热门讨论话题
识别75个不同的话题类别
客户服务
客服对话分析
分类客户咨询的主要话题
提高客服响应效率
🚀 chat_topics
这是一个 BERTopic 模型。BERTopic 是一个灵活且模块化的主题建模框架，可从大型数据集中生成易于解释的主题。
🚀 快速开始
要使用此模型，你需要先安装 BERTopic：
pip install -U bertopic
你可以按以下方式使用该模型：
from bertopic import BERTopic
topic_model = BERTopic.load("davanstrien/chat_topics")
topic_model.get_topic_info()
✨ 主要特性
主题概述
- 主题数量：75
- 训练文档数量：63530
点击此处查看所有主题概述。
| 主题 ID | 主题关键词 | 主题频率 | 标签 |
|---|---|---|---|
| -1 | provide - using - information - sure - help | 26 | -1_provide_using_information_sure |
| 0 | openai - ai - chatgpt - assistant - language | 7837 | 生成式人工智能 |
| 1 | anytime - welcome - assistance - helpful - thank | 1342 | 1_anytime_welcome_assistance_helpful |
| 2 | quantum - particle - physics - particles - relativity | 778 | 物理学 |
| 3 | story - lived - life - novel - felt | 569 | 3_story_lived_life_novel |
| 4 | letter - sincerely - regards - email - dear | 516 | 4_letter_sincerely_regards_email |
| 5 | rust - haskell - programming - java - languages | 504 | 编程 |
| 6 | css - html - style - div - js | 494 | 网页编程 |
| 7 | linux - ubuntu - debian - fedora - install | 440 | 7_linux_ubuntu_debian_fedora |
| 8 | recipe - bake - ingredients - baking - dough | 425 | 8_recipe_bake_ingredients_baking |
| 9 | websocket - json - socket - api - discord | 425 | 9_websocket_json_socket_api |
| 10 | communism - capitalism - marx - economic - economy | 424 | 10_communism_capitalism_marx_economic |
| 11 | dog - pet - breed - breeds - pets | 408 | 11_dog_pet_breed_breeds |
| 12 | philosophy - theological - philosophical - beliefs - consciousness | 394 | 12_philosophy_theological_philosophical_beliefs |
| 13 | git - github - repository - software - commit | 381 | 13_git_github_repository_software |
| 14 | music - songs - musical - lyrics - song | 370 | 14_music_songs_musical_lyrics |
| 15 | devops - development - developers - industry - develop | 323 | 15_devops_development_developers_industry |
| 16 | pythagorean - hypotenuse - triangle - math - sqrt | 302 | 16_pythagorean_hypotenuse_triangle_math |
| 17 | eu - europe - economy - economic - war | 291 | 17_eu_europe_economy_economic |
| 18 | sleep - asleep - bedtime - procrastination - depression | 280 | 18_sleep_asleep_bedtime_procrastination |
| 19 | kramer - seinfeld - jerry - cafe - elaine | 279 | 19_kramer_seinfeld_jerry_cafe |
| 20 | printing - prints - printer - print - printers | 276 | 20_printing_prints_printer_print |
| 21 | influenza - flu - panic - symptoms - medical | 251 | 21_influenza_flu_panic_symptoms |
| 22 | chess - chessboard - practice - strategy - learn | 242 | 22_chess_chessboard_practice_strategy |
| 23 | algorithm - primes - array - integers - python | 240 | 23_algorithm_primes_array_integers |
| 24 | youtube - viewers - media - google - streaming | 240 | 24_youtube_viewers_media_google |
| 25 | poison - chemicals - powder - turpentine - smoke | 226 | 25_poison_chemicals_powder_turpentine |
| 26 | monday - sunday - count_weekend_days - calendar - dates | 216 | 26_monday_sunday_count_weekend_days_calendar |
| 27 | colors - colour - color - pigments - blue | 208 | 27_colors_colour_color_pigments |
| 28 | roman - attila - rome - empire - warfare | 205 | 28_roman_attila_rome_empire |
| 29 | investing - investments - investment - stocks - financial | 204 | 29_investing_investments_investment_stocks |
| 30 | vocabulary - wordle - words - scrabble - word | 201 | 30_vocabulary_wordle_words_scrabble |
| 31 | planets - sun - earth - planet - pluto | 198 | 31_planets_sun_earth_planet |
| 32 | renewable - solar - electricity - energy - electrical | 190 | 32_renewable_solar_electricity_energy |
| 33 | pygame - ball_radius - draw - circle - canvas | 181 | 33_pygame_ball_radius_draw_circle |
| 34 | fishing - fish - boat - hiking - camping | 176 | 34_fishing_fish_boat_hiking |
| 35 | gpus - gpu - motherboard - cpu - hardware | 162 | 35_gpus_gpu_motherboard_cpu |
| 36 | hvac - remodeling - energy - kwh - housing | 159 | 36_hvac_remodeling_energy_kwh |
| 37 | database - graphql - databases - postgresql - sql | 159 | 37_database_graphql_databases_postgresql |
| 38 | información - significado - cómo - como - sistemas | 158 | 38_información_significado_cómo_como |
| 39 | motherboard - pcie - gpu - bios - computer | 153 | 39_motherboard_pcie_gpu_bios |
| 40 | crops - produce - planting - peppers - plants | 148 | 40_crops_produce_planting_peppers |
| 41 | paintings - art - modernist - artists - modern | 148 | 41_paintings_art_modernist_artists |
| 42 | workout - exercises - dumbbells - dumbbell - exercise | 147 | 42_workout_exercises_dumbbells_dumbbell |
| 43 | climate - warming - pollution - environmental - emissions | 142 | 43_climate_warming_pollution_environmental |
| 44 | coffee - espresso - brewing - tea - beans | 137 | 44_coffee_espresso_brewing_tea |
| 45 | velocity - drag - acceleration - density - formula | 132 | 45_velocity_drag_acceleration_density |
| 46 | woodchuck - woodchucks - units - kilogram - kilograms | 130 | 46_woodchuck_woodchucks_units_kilogram |
| 47 | ascii - glyphs - hiragana - art - font | 129 | 47_ascii_glyphs_hiragana_art |
| 48 | guitars - guitar - strings - guitarists - instrument | 127 | 48_guitars_guitar_strings_guitarists |
| 49 | tallest - buildings - building - burj - khalifa | 114 | 49_tallest_buildings_building_burj |
| 50 | flat - earth - curvature - spherical - tectonic | 111 | 50_flat_earth_curvature_spherical |
| 51 | essay - awareness - understanding - being - be | 102 | 51_essay_awareness_understanding_being |
| 52 | portals - ender - portal - obsidian - netherite | 102 | 52_portals_ender_portal_obsidian |
| 53 | android - apple - phones - devices - vehicles | 101 | 53_android_apple_phones_devices |
| 54 | fasting - dietary - diet - eating - metabolic | 101 | 54_fasting_dietary_diet_eating |
| 55 | meditation - relief - pain - health - nociception | 99 | 55_meditation_relief_pain_health |
| 56 | weather - forecast - forecasts - raining - precipitation | 95 | 56_weather_forecast_forecasts_raining |
| 57 | president - presidents - presidency - constitution - biden | 94 | 57_president_presidents_presidency_constitution |
| 58 | no - nope - yes - not - maybe | 94 | 58_no_nope_yes_not |
| 59 | peregrine - airspeed - falcon - speed - bird | 90 | 59_peregrine_airspeed_falcon_speed |
| 60 | crontab - cron - myscript - script - bash | 83 | 60_crontab_cron_myscript_script |
| 61 | youtuber - streamer - ceo - musk - founder | 83 | 61_youtuber_streamer_ceo_musk |
| 62 | layovers - flights - circumnavigate - layover - travel | 83 | 62_layovers_flights_circumnavigate_layover |
| 63 | keyboards - keyboard - switches - qwerty - types | 83 | 63_keyboards_keyboard_switches_qwerty |
| 64 | file_path_in_dir1 - file_path1 - csv_file - file_path_in_dir2 - file_path2 | 80 | 64_file_path_in_dir1_file_path1_csv_file_file_path_in_dir2 |
| 65 | pele - maradona - lebron - ronaldo - nba | 76 | 65_pele_maradona_lebron_ronaldo |
| 66 | alopecia - hairstyles - hairstyle - hair - scalp | 66 | 66_alopecia_hairstyles_hairstyle_hair |
| 67 | nginx - docker - kubernetes - proxy_pass - nodeport | 65 | 67_nginx_docker_kubernetes_proxy_pass |
| 68 | directories - directory - sudo - filesystem - folders | 62 | 68_directories_directory_sudo_filesystem |
| 69 | gps - map - geocaching - maps - armenia | 52 | 69_gps_map_geocaching_maps |
| 70 | meiosis - mitosis - fertilization - reproduction - ovulation | 51 | 70_meiosis_mitosis_fertilization_reproduction |
| 71 | colleges - admissions - universities - campus - university | 43 | 71_colleges_admissions_universities_campus |
| 72 | unicorns - unicorn - pony - ponies - mythical | 32 | 72_unicorns_unicorn_pony_ponies |
| 73 | superpowers - abilities - superhero - superhuman - powers | 28 | 73_superpowers_abilities_superhero_superhuman |
训练超参数
- calculate_probabilities: False
- language: None
- low_memory: False
- min_topic_size: 20
- n_gram_range: (1, 1)
- nr_topics: 75
- seed_topic_list: None
- top_n_words: 10
- verbose: True
框架版本
| 属性 | 详情 |
|---|---|
| 模型类型 | BERTopic 主题建模模型 |
| 训练数据 | OpenAssistant/oasst1 |
| Numpy 版本 | 1.22.4 |
| HDBSCAN 版本 | 0.8.29 |
| UMAP 版本 | 0.5.3 |
| Pandas 版本 | 1.5.3 |
| Scikit-Learn 版本 | 1.2.2 |
| Sentence-transformers 版本 | 2.2.2 |
| Transformers 版本 | 4.29.2 |
| Numba 版本 | 0.56.4 |
| Plotly 版本 | 5.13.1 |
| Python 版本 | 3.10.11 |
📄 许可证
本项目采用 MIT 许可证。
Distilbert Base Uncased Finetuned Sst 2 English
Apache-2.0
基于DistilBERT-base-uncased在SST-2情感分析数据集上微调的文本分类模型，准确率91.3%
文本分类 English
D
distilbert
5.2M
746
Xlm Roberta Base Language Detection
MIT
基于XLM-RoBERTa的多语言检测模型，支持20种语言的文本分类
文本分类
Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesX
papluca
2.7M
333
Roberta Hate Speech Dynabench R4 Target
该模型通过动态生成数据集来改进在线仇恨检测，专注于从最差案例中学习以提高检测效果。
文本分类 Transformers English
Transformers EnglishR
facebook
2.0M
80
Bert Base Multilingual Uncased Sentiment
MIT
基于bert-base-multilingual-uncased微调的多语言情感分析模型，支持6种语言的商品评论情感分析
文本分类 Supports Multiple Languages
B
nlptown
1.8M
371
Emotion English Distilroberta Base
基于DistilRoBERTa-base微调的英文文本情感分类模型，可预测埃克曼六种基本情绪及中性类别。
文本分类 Transformers English
Transformers EnglishE
j-hartmann
1.1M
402
Robertuito Sentiment Analysis
基于RoBERTuito的西班牙语推文情感分析模型，支持POS(积极)/NEG(消极)/NEU(中性)三类情感分类
文本分类 Spanish
R
pysentimiento
1.0M
88
Finbert Tone
FinBERT是一款基于金融通讯文本预训练的BERT模型，专注于金融自然语言处理领域。finbert-tone是其微调版本，用于金融情感分析任务。
文本分类 Transformers English
Transformers EnglishF
yiyanghkust
998.46k
178
Roberta Base Go Emotions
MIT
基于RoBERTa-base的多标签情感分类模型，在go_emotions数据集上训练，支持28种情感标签识别。
文本分类 Transformers English
Transformers EnglishR
SamLowe
848.12k
565
Xlm Emo T
XLM-EMO是一个基于XLM-T模型微调的多语言情感分析模型，支持19种语言，专门针对社交媒体文本的情感预测。
文本分类 Transformers Other
Transformers OtherX
MilaNLProc
692.30k
7
Deberta V3 Base Mnli Fever Anli
MIT
基于MultiNLI、Fever-NLI和ANLI数据集训练的DeBERTa-v3模型，擅长零样本分类和自然语言推理任务
文本分类 Transformers English
Transformers EnglishD
MoritzLaurer
613.93k
204
Featured Recommended AI Models
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型，性能媲美GPT-3.5-turbo，优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型 Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型，专为边缘设备推理设计，体积仅为Cosmo-3B模型的2%左右。
对话系统 Transformers English
Transformers EnglishC
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型，适用于从给定文本中提取答案的任务。
问答系统 Chinese
R
uer
2,694
98