Edit model card

bertopic-crypto-topic-modeling

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("iMahdiGhazavi/bertopic-crypto-topic-modeling")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 50
  • Number of training documents: 4000
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 bitcoin - btc - crypto - buy - cryptocurrency 10 -1_bitcoin_btc_crypto_buy
0 around - see - would - bitcoin - go 1215 0_around_see_would_bitcoin
1 bitcoin - buy - fix - want - love 363 1_bitcoin_buy_fix_want
2 project - airdrop - team - great - always 304 2_project_airdrop_team_great
3 covidvaccine - covid - vaccine - dose - get 288 3_covidvaccine_covid_vaccine_dose
4 interoperable - struggle - libonomy - link - coin 275 4_interoperable_struggle_libonomy_link
5 airdrop - bsc - airdropinspector - dinowallet - binancesmartchain 134 5_airdrop_bsc_airdropinspector_dinowallet
6 binancesmartchain - binance - pancakeswap - tg - launchedjoin 129 6_binancesmartchain_binance_pancakeswap_tg
7 cryptocurrency - gt - denation - crypto - btc 98 7_cryptocurrency_gt_denation_crypto
8 bitcoin - giveaway - opt - scalp - short 94 8_bitcoin_giveaway_opt_scalp
9 tradingview - thought - idea - binancebtcusdt - trade 62 9_tradingview_thought_idea_binancebtcusdt
10 dev - everrise - core - utility - everown 61 10_dev_everrise_core_utility
11 cryptocurrencie - technology - fintech - morbex - money 53 11_cryptocurrencie_technology_fintech_morbex
12 bitfinex - rebound - spike - record - crash 51 12_bitfinex_rebound_spike_record
13 link - doge - eth - sol - update 50 13_link_doge_eth_sol
14 positionv - entry - target - stop - signal 47 14_positionv_entry_target_stop
15 bet - odd - betting - gamblingtwitter - wager 43 15_bet_odd_betting_gamblingtwitter
16 plastic - ico - investment - arno - plasticfinance 40 16_plastic_ico_investment_arno
17 kitkart - addressovwmdgywzcvyqundajjrnjatchpre - io - android - donate 37 17_kitkart_addressovwmdgywzcvyqundajjrnjatchpre_io_android
18 davido - igbo - delivery - ibadan - giroud 37 18_davido_igbo_delivery_ibadan
19 crush - superb - preserve - competition - completely 34 19_crush_superb_preserve_competition
20 coinhuntworld - vault - location - awesome - play 32 20_coinhuntworld_vault_location_awesome
21 tweet - follow - tone - tips - insight 32 21_tweet_follow_tone_tips
22 malaysia - miner - btcusd - crush - hourly 31 22_malaysia_miner_btcusd_crush
23 currently - breathe - jumpy - dismiss - mofos 31 23_currently_breathe_jumpy_dismiss
24 change - coinbase - pro - worried - month 30 24_change_coinbase_pro_worried
25 cryptonews - rixx - ethereum - mover - report 28 25_cryptonews_rixx_ethereum_mover
26 ksi - superstar - lose - jj - youtube 28 26_ksi_superstar_lose_jj
27 block - tx - tictoknextblock - recipient - gmt 28 27_block_tx_tictoknextblock_recipient
28 ape - nftcommunity - nftartist - nftart - nftcollector 23 28_ape_nftcommunity_nftartist_nftart
29 onestop - legendary - trading - shop - usdt 22 29_onestop_legendary_trading_shop
30 america - client - bank - illegal - petroleum 22 30_america_client_bank_illegal
31 fence - bear - long - market - last 18 31_fence_bear_long_market
32 forex - invest - business - stock - entrepreneur 18 32_forex_invest_business_stock
33 avg - hour - xbt - xbtusd - information 17 33_avg_hour_xbt_xbtusd
34 pumping - challenge - cryptos - recover - interested 17 34_pumping_challenge_cryptos_recover
35 price - current - agree - bitcoin - early 17 35_price_current_agree_bitcoin
36 account - procedure - immediately - worry - management 16 36_account_procedure_immediately_worry
37 credit - card - fast - exchange - xrp 16 37_credit_card_fast_exchange
38 day - avg - move - low - high 15 38_day_avg_move_low
39 bonus - startup - person - hi - dm 15 39_bonus_startup_person_hi
40 last - price - drop - compare - right 14 40_last_price_drop_compare
41 usd - safemoon - price - dogecoin - ethereum 14 41_usd_safemoon_price_dogecoin
42 donation - willing - collect - initial - monetary 14 42_donation_willing_collect_initial
43 value - decrease - euro - last - lose 14 43_value_decrease_euro_last
44 token - bll - billiontoken - milliontoken - milion 14 44_token_bll_billiontoken_milliontoken
45 help - address - xdecbdabddbe - dear - hi 13 45_help_address_xdecbdabddbe_dear
46 technicalanalysis - technical - analysis - jpy - eur 13 46_technicalanalysis_technical_analysis_jpy
47 xddddabd - emojiday - cryptogiveaway - giveaway - amp 12 47_xddddabd_emojiday_cryptogiveaway_giveaway
48 asic - cryptomine - yieldfarming - bitcoinmine - tool 11 48_asic_cryptomine_yieldfarming_bitcoinmine

Training hyperparameters

  • calculate_probabilities: True
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: 50
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 1.25.2
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.6
  • Pandas: 2.0.3
  • Scikit-Learn: 1.2.2
  • Sentence-transformers: 2.6.1
  • Transformers: 4.38.2
  • Numba: 0.58.1
  • Plotly: 5.15.0
  • Python: 3.10.12
Downloads last month
40