geektech's picture
Add BERTopic model
9e6e2b4 verified
---
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
---
# BERTopic-Israel-Palestine-Description
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("geektech/BERTopic-Israel-Palestine-Description")
topic_model.get_topic_info()
```
## Topic overview
* Number of topics: 33
* Number of training documents: 1369
<details>
<summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|----------|----------------|-----------------|-------|
| -1 | the - https - com - and - to | 12 | -1_the_https_com_and |
| 0 | palestine - celebrities - support - israel - the | 419 | 0_palestine_celebrities_support_israel |
| 1 | hamas - the - hostages - https - and | 106 | 1_hamas_the_hostages_https |
| 2 | com - https - hamas - news - firstpost | 84 | 2_com_https_hamas_news |
| 3 | news - www tv9hindi - https www tv9hindi - tv9hindi - tv9hindi com | 79 | 3_news_www tv9hindi_https www tv9hindi_tv9hindi |
| 4 | trendingnow - news breakingnews - news - the - breakingnews | 46 | 4_trendingnow_news breakingnews_news_the |
| 5 | bendera - menggambarbendera - menggambar - palestina - prayforpalestine | 45 | 5_bendera_menggambarbendera_menggambar_palestina |
| 6 | israel - humanity - the - news - palestine | 44 | 6_israel_humanity_the_news |
| 7 | the - and - this - in - to | 41 | 7_the_and_this_in |
| 8 | reviews - news movie - produce - retroluxe - movie | 39 | 8_reviews_news movie_produce_retroluxe |
| 9 | https - com - ajplus - on - www | 34 | 9_https_com_ajplus_on |
| 10 | allah - allah di - gaza - pertolongan - pertolongan allah | 29 | 10_allah_allah di_gaza_pertolongan |
| 11 | piers - piers morgan - morgan - shorts - podcast | 28 | 11_piers_piers morgan_morgan_shorts |
| 12 | the - to - freepalestine - it - africa | 26 | 12_the_to_freepalestine_it |
| 13 | the - crisis - conflict - and - international relations | 23 | 13_the_crisis_conflict_and |
| 14 | https - com - https bit - https bit ly - bit ly | 22 | 14_https_com_https bit_https bit ly |
| 15 | the - genocide - israel - gaza - of | 22 | 15_the_genocide_israel_gaza |
| 16 | sakura - palestina - sakura school - drama sakura school simulator - school simulator | 21 | 16_sakura_palestina_sakura school_drama sakura school simulator |
| 17 | middleeasteye - com middleeasteye - https - com - us on | 20 | 17_middleeasteye_com middleeasteye_https_com |
| 18 | status - whatsapp - shorts - countries - shorts shorts | 19 | 18_status_whatsapp_shorts_countries |
| 19 | ronaldo - palestine - footballers - support - israel | 19 | 19_ronaldo_palestine_footballers_support |
| 20 | the - voanews - of - on - https | 18 | 20_the_voanews_of_on |
| 21 | israel - gaza - palestine - news - war | 18 | 21_israel_gaza_palestine_news |
| 22 | the - on - in - to - of | 17 | 22_the_on_in_to |
| 23 | israel - malayalam - palestine - war - malayalam israel | 17 | 23_israel_malayalam_palestine_war |
| 24 | bts - khan sir - sir - khan - video | 17 | 24_bts_khan sir_sir_khan |
| 25 | https - com - us on - us - www | 17 | 25_https_com_us on_us |
| 26 | the - history - of - pyramids - of the | 16 | 26_the_history_of_pyramids |
| 27 | russian - nbc - nbcnews - arma - nbc news | 15 | 27_russian_nbc_nbcnews_arma |
| 28 | news - bit ly - bit - ly - the | 15 | 28_news_bit ly_bit_ly |
| 29 | palestine - israel - palestine israel - celebrities - israel palestine | 14 | 29_palestine_israel_palestine israel_celebrities |
| 30 | liriklagu - lirikgoogle - fypシ - lirik - liriklagu lirikgoogle | 14 | 30_liriklagu_lirikgoogle_fypシ_lirik |
| 31 | the - force - and - of - com | 13 | 31_the_force_and_of |
</details>
## Training hyperparameters
* calculate_probabilities: False
* language: multilingual
* low_memory: False
* min_topic_size: 10
* n_gram_range: (1, 4)
* nr_topics: None
* seed_topic_list: None
* top_n_words: 25
* verbose: False
* zeroshot_min_similarity: 0.7
* zeroshot_topic_list: None
## Framework versions
* Numpy: 1.24.3
* HDBSCAN: 0.8.33
* UMAP: 0.5.5
* Pandas: 2.1.4
* Scikit-Learn: 1.2.2
* Sentence-transformers: 2.3.1
* Transformers: 4.36.2
* Numba: 0.58.1
* Plotly: 5.16.1
* Python: 3.10.12