metadata
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
C1-topic-model-100
This is a 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:
from bertopic import BERTopic
topic_model = BERTopic.load("AlexanderHolmes0/C1-topic-model-100")
topic_model.get_topic_info()
An example of the Chat GPT - 3.5 Turbo representations:
Topic overview
- Number of topics: 100
- Number of training documents: 112332
Click here for an overview of all topics.
| Topic | Representation | Count | ChatGPT |
|---|---|---|---|
| -1 | ['stop', 'people', 'need', 'help', 'banking', 'like', 'work', 'business', 'money', 'make'] | 4738 | ['Issues with Capital One credit card accounts'] |
| 0 | ['account', 'card', 'customer', 'service', 'phone', 'credit', 've', 'payment', 'help', 'number'] | 21155 | ['Poor customer service experiences with @user customer support'] |
| 1 | ['game', 'thank', 'win', 'team', 'bazinga_sb', 'thanks', 'play', 'lounge', 'congrats', 'hype'] | 11918 | ['tickets for a game with bazinga_sb song and rafael nadal.'] |
| 2 | ['app', 'need', 'stop', 'help', 'lol', 'shit', 'ok', 'like', 'cares', 'guys'] | 11946 | ['Social media engagement and links'] |
| 3 | ['card', 'credit', 'account', 'customer', 'told', 'company', 'payment', 'called', 'service', 'capitol'] | 6152 | ['Capital One account and customer service issues'] |
| 4 | ['friend', 'request', 'friends', 'send', 'mind', 'profile', 'facebook', 'sending', 'don', 'hello'] | 3403 | ['Friend Request Difficulties on Facebook'] |
| 5 | ['community', 'event', 'lounge', 'thank', 'presented', 'program', 'food', 'business', 'join', 'suppo'] | 4398 | ['Capital One Community Food Event Program'] |
| 6 | ['trading', 'whatsapp', 'forex', 'investment', 'profit', 'trade', 'invest', 'contact', 'crypto', 'trader'] | 2804 | ['investment opportunities in forex, bitcoin, and binary options'] |
| 7 | ['', '', '', '', '', '', '', '', '', ''] | 1191 | ['Dealing with Old Debt and Financial Expenses'] |
| 8 | ['ho', 'genial', 'travolta', 'john', 'love', 'shimmmerrrr', 'lovettt', 'nnniiiccceeeee', 'vjjbnm', 'listos'] | 1157 | ['Wonderful class with great DC Ben'] |
| 9 | ['santa', 'john', 'travolta', 'love', 'movie', 'christmas', 'ho', 'moves', 'claus', 'sexy'] | 1695 | ['Love for John Travolta at Christmas ๐ '] |
| 10 | ['que', 'en', 'la', 'para', 'el', 'es', 'una', 'por', 'los', 'mi'] | 1532 | ['Financial Tips and Christmas Shopping Experiences'] |
| 11 | ['worst', 'service', 'company', 'customer', 'bank', 'horrible', 'terrible', 'card', 'account', 'don'] | 2417 | ['worst customer service in banking industry'] |
| 12 | ['love', 'awesome', 'happy', 'best', 'great', 'brilliant', 'wow', 'bihday', 'cool', 'amen'] | 2736 | ['Topic: Feeling Awesome and Happy!'] |
| 13 | ['people', 'blessed', 'grands', 'cus', 'paying', 'stay', 'hard', 'god', 'struggling', 'message'] | 896 | ['Support for People Going Through Hard Times'] |
| 14 | ['later', 'connect', 'definitely', 'inbox', 'hello', 'thank', 'mr', 'message', 'll', 'hi'] | 4157 | ['Referrals to Mr. Christopher O. Thompson and Mr. Robes Kenny'] |
| 15 | ['shimmerr', 'kt', 'txscapitalone', 'capit', 'word', 'givaway', 'bejeweled', 'shine', 'ts', 'girl'] | 535 | ["Customer Service Dispute with Capitol One and Cabela's"] |
| 16 | ['credit', 'card', 'score', 'limit', 'pay', 'balance', 'cards', 'increase', 'payment', 'personal'] | 5072 | ['Personal vs Business Credit Repossession Concerns'] |
| 17 | ['spell', 'dr', 'caster', 'ex', 'lover', 'marriage', 'husband', 'love', 'relationship', 'page'] | 672 | ['Relationship Reconciliation with Spell Casters'] |
| 18 | ['love', 'business', 'thank', 'credit', 'best', 'card', 'bank', 'great', 'capitol', 'cards'] | 2133 | ['capital one customer satisfaction and feedback ๐'] |
| 19 | ['links', 'mm', 'click', 'nutshell', 'join', 'corey', 'referral', 'unabridged', 'gelmtree', 'chainzz'] | 515 | ['http'] |
| 20 | ['travel', 'points', 'venture', 'miles', 'flights', 'trip', 'flight', 'book', 'bonus', 'card'] | 1271 | ['Travel Credit Card Rewards'] |
| 21 | ['slash', 'guitar', 'guitarist', 'riff', 'song', 'play', 'solo', 'guns', 'playing', 'roses'] | 630 | ["Critique of Guitarist's Performance in Playing Rock Song"] |
| 22 | ['reachout', 'miller', 'david', 'comes', 'investing', 'financial', 'help', 'diane', 'diana', 'christine'] | 303 | ['Investing assistance from David Miller'] |
| 23 | ['preston', 'mourning', 'underneath', 'commenting', 'kelly', 'clicking', 'loss', 'management', 'wife', 'travolta'] | 211 | ["Mourning of John Travolta's Wife Kelly Preston"] |
| 24 | ['tnt', 'qbs', 'reminded', 'tune', 'headed', 'vegas', 'tweet', 'june', 'time', 'banners'] | 222 | ['Tune into Vegas QB Match on TNT in June'] |
| 25 | ['working', 'website', 'isn', 'expired', 'enter', 'app', 'haven', 'gotten', 'doesn', 'work'] | 947 | ['Issues with link receipt'] |
| 26 | ['suck', 'sucks', 'lol', 'fake', 'sounds', 'joke', 'trash', 'stupid', 'bad', 'shit'] | 1603 | ['Sounds like a terrible joke'] |
| 27 | ['love', 'cute', 'absolutely', 'ittttt', 'lovelove', 'loveeeee', 'song', 'grandkids', 'awesome', 'dancing'] | 292 | ['love love it - stuff, kids, emails, easy, stop, sending, times, best'] |
| 28 | ['mobile', 'app', 'digital', 'options', 'shopping', 'set', 'safely', 'card', 'banking', 'phone'] | 554 | ['Managing Digital Payment Options on the Capital One Mobile App'] |
| 29 | ['cardigan', 'flannel', 'plaid', 'tsxccapitalone', 'cardigans', 'caedigan', 'taxcaptialone', 'ysxcapitalone', 'robe', 'tsxcapit'] | 191 | ['travel mug in red table'] |
| 30 | ['presale', 'event', 'taylorswift', 'venue', 'np', 'cardholder', 'events', 'gain', 'staing', 'stas'] | 403 | ['Capital One Cardholder Presale Event Details'] |
| 31 | ['donna', 'pescow', 'annette', 'fever', 'looks', 'saturday', 'cameo', 'movie', 'night', 'actress'] | 340 | ['Donna Pescow in Saturday Night Movie - Love Seeing Her!'] |
| 32 | ['card', 'best', 'great', 'love', 'cards', 'got', 'credit', 'better', 'chase', 'good'] | 632 | ['best credit card love'] |
| 33 | ['flannel', 'flannnel', 'scymbags', 'rsxcapitalone', 'pumpkinseason', 'xgiveaway', 'tsxca', 'fallvibes', 'tsxcpaitalone', 'cozyflannel'] | 172 | ['Fall Spirit through Cozy Flannel and Pumpkin Treats'] |
| 34 | ['car', 'auto', 'navigator', 'cars', 'buying', 'vehicle', 'dealership', 'truck', 'pre', 'suv'] | 566 | ['Car Buying with Capital One Auto Navigator'] |
| 35 | ['๐๐๐บ๐', '๐บ๐๐ฝ', '๐๐๐', '๐๐๐', '๐๐', '๐บ๐ผ๐ผ๐๐๐๐', '๐๐๐๐', '๐ผ๐๐๐๐๐๐๐๐', '๐๐๐พ', '๐ฒ๐จ๐ฎ'] | 416 | ['Business and Capital Verification Service'] |
| 36 | ['sure', 'true', 'correct', 'yessir', 'yea', 'yessssss', 'yess', 'yesss', 'duh', 'thank'] | 329 | ['user saying yes and hi'] |
| 37 | ['beard', 'chef', 'awards', 'beardfoundation', 'james', 'restaurant', 'presented', 'chefs', 'taste', 'jbfa'] | 223 | ['James Beard Awards Restaurant and Chef Semifinalists Congratulated'] |
| 38 | ['worst', 'bank', 'service', 'customer', 'fucking', 'hate', 'banking', 'trash', 'company', 'worse'] | 1098 | ['@user labeled as the worst bank in banking industry'] |
| 39 | ['bank', 'banks', 'banking', 'best', 'chairman', 'branches', 'chairperson', 'great', 'dg', 'atms'] | 397 | ["Banking with Barry Watts's Gray Bank"] |
| 40 | ['student', 'unlimited', 'key', 'quicksilver', 'cash', 'savorone', 'earning', 'earn', 'enteainment', 'presents'] | 343 | ['Capital One Quicksilver Student Card - Earn Unlimited Cash Back on Purchases'] |
| 41 | ['teambradgers', 'hardwood', 'winning', 'head', 'winners', 'congratulations', 'luck', 'came', 'close', 'better'] | 178 | ['Winners of capitalonesthematch and better luck on the hardwood'] |
| 42 | ['giveway', 'tstheerastour', 'tsxcapitalone', 'givesway', 'givaway', 'leopard', 'tscott', 'giveaway', 'tsxcapital', 'ts'] | 155 | ['capitalone giveaway, user love, comment'] |
| 43 | ['love', 'awesome', 'cute', 'omg', 'absolutely', 'cool', 'oh', 'niiice', 'loooovvve', 'fantastic'] | 386 | ['Love it! Absolutely the best.'] |
| 44 | ['postdoctoral', 'ฮบฮฑฮน', '๐ญ๐จ', '๐๐ง๐', 'ุฑุณูู', '๐๐๐๐', 'ฮฝฮฑ', 'mr', '๐๐๐พ', 'ใ คใ ค'] | 357 | ['Farm and School Fan Business Featuring Tom and Sky'] |
| 45 | ['platinum', 'excluded', 'cards', 'credit', 'secured', 'card', 'mastercard', 'creditstacks', 'crรฉdito', 'deposit'] | 127 | ['platinum credit cards exclusion'] |
| 46 | ['solving', 'ai', 'data', 'methods', 'learning', 'oracle', 'systems', 'algebraic', 'etem', 'machine'] | 219 | ['deep learning systems for business decision management'] |
| 47 | ['dm', 'sent', 'haven', 'gotten', 'dms', 'check', 'received', 'response', 'answer', 'reply'] | 289 | ['Direct Message (DM) Response Issues'] |
| 48 | ['nice', 'cool', 'good', 'cute', 'dimples', 'pretty', 'funny', 'lovely', 'hello', 'hey'] | 206 | ['Based on the provided information, a suitable short topic label would be:\n\nA Nice Version of Epic Played Wow'] |
| 49 | ['cafรฉs', 'branches', 'offices', 'closed', 'holiday', 'app', 'recognition', 'celebration', 'january', 'observance'] | 130 | ['Capital One holiday closure announcement'] |
| 50 | ['gt', 'page', 'javier', 'facebook', 'sergio', 'boutique', 'account', 'salvation', 'chalk', 'steps'] | 191 | ['Verification and Deactivation Notices for Facebook Pages'] |
| 51 | ['fault', 'mailbox', 'buyer', 'flood', 'vendors', 'loves', 'costs', 'fyi', 'shady', 'lines'] | 89 | ['Shady Business Practices and Warning to Avoid using Company for Credit Lines'] |
| 52 | ['responsibility', 'expect', 'accept', 'unethical', 'perjury', 'business', 'involved', 'guilty', 'abusing', 'purposes'] | 88 | ['Expectation of Responsibility from Capital One'] |
| 53 | ['holiday', 'encore', 'noรซl', 'livestream', 'songs', 'album', 'spirit', 'performance', 'featuring', 'season'] | 44 | ['Get into the holiday spirit with a livestream performance by local artist Dan Brown!'] |
| 54 | ['bio', 'webinar', 'mcws', 'capitalonecafe', 'wcwsselfie', 'program', 'unprecedented', 'predictable', 'brand', 'capitalize'] | 565 | ['Capital One Annual Picture Project ๐ธ'] |
| 55 | ['agree', 'true', 'haha', 'ha', 'right', 'mendez', 'dianna', 'sure', 'yea', 'exactly'] | 324 | ['"Yes, Smith, Yeah, Correct, Really, Definitely, Right, Carol, Moore, Brian"'] |
| 56 | ['word', 'code', 'shib', 'enter', 'biiiish', 'shimma', 'shimmerr', 'txscapitalone', 'gotta', 'hashtags'] | 113 | ['Beauty and Connection'] |
| 57 | ['uber', 'eats', 'complimentary', 'orders', 'nov', 'membership', 'eligible', 'unlimited', 'terms', 'cardholders'] | 46 | ['Uber Cash Back Promotion for Capital One Cardholders'] |
| 58 | ['bbb', 'tracker', 'scams', 'scam', 'scamtracker', 'bbbscamtracker', 'org', 'amazon', 'detect', 'protect'] | 85 | ['Scam Protection with BBB Scam Tracker'] |
| 59 | ['count', 'days', 'fucking', 'bitch', 'fuckin', 'counting', 'yall', 'ups', 'ur', 'numbered'] | 89 | ['count your days'] |
| 60 | ['tradelines', 'cpn', 'repair', 'removal', 'inquiries', 'sba', 'score', 'loans', 'boosting', 'credit'] | 102 | ['credit score improvement and related services'] |
| 61 | ['gas', 'prices', 'inflation', 'cars', 'electric', 'gasoline', 'falling', 'climbing', 'electricity', 'economy'] | 159 | ['Gas prices falling trend'] |
| 62 | ['spark', 'antonelli', 'preset', 'cash', 'cheese', 'unlimited', 'helps', 'shop', 'spending', 'grow'] | 57 | ['Spark Cash Plus card helping Antonelliโs Cheese Shop grow its business'] |
| 63 | ['waiting', 'room', 'queue', 'open', 'lounge', 'wait', 'denver', 'elevator', 'does', 'presale'] | 455 | ['Waiting room location query'] |
| 64 | ['need', 'want', 'got', 'officce', 'wish', 'rhode', 'interested', 'waiting', 'waverly', 'needs'] | 371 | ['In need of assistance'] |
| 65 | ['taher', 'bapary', 'abu', 'wow', 'baah', 'testyes', 'relaxday', 'ernest', 'videos', 'flower'] | 46 | ['abu taher bapary - online excitement ๐๐ก๐'] |
| 66 | ['atos', 'story', 'cloud', 'datacenter', 'upl', 'transformative', 'wp', 'laid', 'personalized', 'content'] | 77 | ['Cloud Transformation Journey for Personalized Customer Experiences'] |
| 67 | ['song', 'itunes', 'radio', 'rainy', 'bts', 'cha', 'ranked', 'uk', 'play', 'hear'] | 163 | ['New BTS song "Rainy Days" topping UK iTunes charts.'] |
| 68 | ['dining', 'cardholders', 'reservations', 'restaurants', 'rated', 'curated', 'reservation', 'culinary', 'rewards', 'sought'] | 69 | ['Capital One dining reservation booking platform for eligible rewards cardholders'] |
| 69 | ['grant', 'apply', 'upfront', 'federal', 'government', 'grants', 'retired', 'program', 'public', 'assistance'] | 103 | ['Grant Applications Without Upfront Payment'] |
| 70 | ['scarf', 'tsgiveaway', 'towel', 'tote', 'bag', 'tstheerastour', 'red', 'beach', 'kept', 'old'] | 53 | ['old red scarf kept from first week'] |
| 71 | ['annual', 'fee', 'fees', 'loffland', 'tam', 'yearly', 'spend', 'year', 'charged', 'pay'] | 204 | ['annual fee inquiry'] |
| 72 | ['unsubcribe', 'mailing', 'stop', 'remove', 'list', 'emails', 'gk', 'removed', 'email', 'unsubscribed'] | 106 | ['user unsubscribe'] |
| 73 | ['crooks', 'money', 'scumbags', 'stole', 'thieves', 'steal', 'fraud', 'counts', 'people', 'scam'] | 633 | ['money scam involving identity theft and federal law enforcement concern'] |
| 74 | ['mcws', 'rebs', 'omaha', 'wps', 'toddy', 'hotty', 'game', 'olemaha', 'hottytoddy', 'hogs'] | 105 | ['Twitter updates from user with the handle "mcws"'] |
| 75 | ['bejeweled', 'ok', 'hi', 'mm', 'tay', 'hola', 'epic', 'ally', 'maria', 'gay'] | 719 | ['ok twin ๐ฅ๐'] |
| 76 | ['pov', 'misclicked', 'clicked', 'clicky', 'pa', 'screen', 'misclick', 'missed', 'did', 'click'] | 174 | ['The Missed Clicky Pa - A Funny Reminder'] |
| 77 | ['financial', 'tips', 'budget', 'empowerment', 'healthy', 'goals', 'literacy', 'money', 'check', 'save'] | 379 | ['Budgeting Tips for Financial Goal Alignment with Bit.ly Links'] |
| 78 | ['wynn', 'match', 'brady', 'hole', 'las', 'tom', 'returns', 'rodgers', 'patrick', 'vegas'] | 70 | ["capital one's the match returns to wynn las vegas for an epic -hole event featuring tom brady and aaron rodgers versus patrick and josh allen"] |
| 79 | ['upgrade', 'upgrades', 'upgraded', 'update', 'seats', 'seat', 'app', 'increase', 'upgradeeee', 'darkmode'] | 142 | ['upgrade randomly with queen and girl, pls'] |
| 80 | ['step', 'tapn', 'wit', 'walking', 'method', 'helped', 'tapp', 'got', 'paid', 'split'] | 120 | ['User Help and Paid Assistance'] |
| 81 | ['facilitate', 'form', 'cybersuppospy', 'communicate', 'following', 'expedite', 'channel', 'dispute', 'suppo', 'promptly'] | 46 | ["Efficient Dispute Resolution Process via Capital One's Online Form"] |
| 82 | ['debt', 'credit', 'need', 'card', 'dm', 'pay', 'debts', 'help', 'bills', 'cards'] | 375 | ['Holiday Credit Card Debt Assistance'] |
| 83 | ['press', 'interactive', 'seat', 'conference', 'hot', 'et', 'qbs', 'questions', 'reply', 'answer'] | 31 | ['Press Conference Interactive Q&A Session'] |
| 84 | ['minority', 'jackie', 'scholarship', 'nation', 'donating', 'premier', 'programs', 'students', 'leadership', 'walk'] | 39 | ['Donation program for minority college students during capital one walk-off season'] |
| 85 | ['chefs', 'chef', 'exclusive', 'dining', 'cardholders', 'recognized', 'viue', 'erick', 'hyde', 'restaurants'] | 30 | ["Exclusive Dining Rewards in Chicago's Hyde Park"] |
| 86 | ['flannel', 'cardigan', 'scarf', 'jk', 'code', 'lol', 'word', 'tis', 'oops', 'seamstr'] | 91 | ['Users confused between flannel and cardigan in a code-related discussion'] |
| 87 | ['sell', 'sold', 'sellout', 'selling', 'tim', 'marketing', 'piece', 'wage', 'saying', 'genius'] | 90 | ['Selling Out - Ultimate Wow factor with Tim and the Boys ๐คท\u200dโ๏ธ'] |
| 88 | ['movie', 'saw', 'watch', 'watching', 'video', 'tv', 'watched', 'love', 'night', 'seen'] | 411 | ['TV show admiration'] |
| 89 | ['denied', 'approved', 'applied', 'pre', 'tried', 'qualify', 'won', 'didn', 'let', 'apply'] | 188 | ['Denied reasons for kick, Matt Smith always getting denied'] |
| 90 | ['balali', 'dizabali', 'manager', 'blame', 'changing', 'bought', 'complete', 'withdrawal', 'oppounity', 'invest'] | 24 | ['Beware of Scams - Life Changing Opportunity with Mrs. Dizabali Balali'] |
| 91 | ['office', 'direct', 'contact', 'don', 'erica', 'renan', 'lizarralde', 'vallecilla', 'kirklnd', 'offices'] | 60 | ['Contacting Capital One Office Direct via Http Links'] |
| 92 | ['stimulus', 'latest', 'mon', 'dates', 'track', 'round', 'government', 'federal', 'grow', 'transferred'] | 23 | ['Tracking latest round of federal stimulus payments from the government on multiple dates'] |
| 93 | ['itbot', 'cash', 'gyvi', 'creditcard', 'best', 'wallethub', 'credit', 'visa', 'mastercard', 'couple'] | 199 | ['Best Travel Credit Card Awards Announcement'] |
| 94 | ['pakistan', 'donate', 'relief', 'flood', 'activities', 'purchase', 'islamabad', 'belgium', 'rawalpindi', 'ptt'] | 27 | ['Flood Relief Donations in Pakistan'] |
| 95 | ['lottery', 'winner', 'jackpot', 'fan', 'million', 'powerball', 'sum', 'funds', 'dollars', 'lucky'] | 77 | ['Powerball jackpot winner blessing fans with funds ๐ฐ๐ฐ'] |
| 96 | ['payments', 'sending', 'email', 'payment', 'suppo', 'mail', 'stop', 'mailed', 'check', 'days'] | 127 | ['Issues with sending payments and lack of email support'] |
| 97 | ['cardholders', 'star', 'mlb', 'ultimate', 'allstarweek', 'giveaways', 'performances', 'official', 'gate', 'highlights'] | 57 | ['MLBยฎ All-Star Weekโข perks for @user cardholders'] |
| 98 | ['reds', 'disparage', 'toss', 'stats', 'count', 'overrated', 'weight', 'pure', 'vccs', 'acquaintd'] | 84 | ['user ratio vs. user tonight'] |
Training hyperparameters
- calculate_probabilities: False
- language: None
- low_memory: False
- min_topic_size: 10
- n_gram_range: (1, 1)
- nr_topics: 100
- seed_topic_list: None
- top_n_words: 10
- verbose: True
Framework versions
- Numpy: 1.26.4
- HDBSCAN: 0.8.33
- UMAP: 0.5.5
- Pandas: 2.0.3
- Scikit-Learn: 1.4.1.post1
- Sentence-transformers: 2.5.1
- Transformers: 4.40.0
- Numba: 0.59.1
- Plotly: 5.20.0
- Python: 3.11.8