Edit model card

reduced_tweets_deforestation_pt

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("thiagoquilice/reduced_tweets_deforestation_pt")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 30
  • Number of training documents: 1444120
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 desmatamento - amaz - nia - de - na 161 Deforestation in Brazil's Amazon region
0 desmatamento - amaz - nia - rt - da 454142 Preventing deforestation in the Amazon
1 por - bolsonaro - rt - do - governo 745274 Political satire and criticism of current events in Brazil
2 dasypodidae - encontrados - familia - costumam - tio 161094 Dasypodidae family found in Brazil
3 noruega - alemanha - nevoa - retiraram - visto 22453 Government policies and rural issues in Brazil
4 de - do - rt - inpe - que 15610 Dasypodidae family found in Brazil
5 artesanais - abdicam - manguezal - pescadores - julga 8545 Environmental disaster in Brazil
6 sat - lite - lan - ado - primeiro 8258 Soja production in Roraima
7 trilh - administram - fundos - imposs - ativos 4441 Protection of the Amazon rainforest
8 deixara - bolsonazi - eleito - entrega - resumiu 3081 Controversial speech or article
9 apres - holanda - ratifica - rejeitar - rcio 2999 Economic rankings of Brazil
10 psicose - subtitles - bertrand - livro - respondendo 2724 Demittance of CNPQ president due to research incentive request
11 venda - herdeira - seguinte - ha - pararam 1855 Preventing Deforestation in the Amazon
12 controlador - blackstone - ceo - schwarzman - steve 1790 Stop Deforestation in the Amazon
13 veneza - look - festival - paz - impactante 1583 Economic impacts of deforestation
14 feminismo - machismo - stica - dom - viol 1300 German President Merkel suspends investments in Amazon due to record deforestation
15 ningu - fala - isso - mais - por 1209 Apocalypse and Ferrous Metals
16 formando - auxiliar - israel - parceria - objetivo 1099 Electoral desmatamento in the Amazon
17 perfume - ingrediente - chanel - vendido - possui 979 Cientista Carlos Nobre na Empresa: Supera Inpe
18 desempregados - comemoravam - motobois - infla - milh 858 Debate over deforestation data
19 finalizei - acompan - infantaria - brigada - velho 674 Agronomic aspects of soybean plant roots
20 ndic - kataguiri - kim - resolvi - desconhece 643 Deforestation in Brazil
21 festa - ulmanos - desejou - bezerros - sacrif 631 Financing for environmental projects in Norway and Germany
22 cristina - tereza - garante - fundi - regulariza 561 Bolsonaro's stance on Amazon deforestation
23 comandados - incapazes - mostraram - receberam - jato 418 Illegal deforestation and burning in the Amazon
24 rcito - ex - higiene - bairros - populares 415 Roman weather in May
25 prontos - quadros - pms - complementar - bons 372 Deforestation in the Amazon in July
26 financiados - desvios - criados - empregos - den 350 Impact of veganism on the Amazon rainforest
27 certif - trading - globais - clientes - chinesa 327 Deforestation monitoring using km and quadrados
28 sequestro - coopera - resgate - isso - pedido 274 Deforestation in the Amazon

Training hyperparameters

  • calculate_probabilities: False
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: 30
  • 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: 0.5.5
  • Pandas: 1.5.3
  • 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
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.