---
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
---

# bertopic-turkish-political

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. 

This model is fine tuned on a custom dataset of Turkish political comments.

## 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("yeniguno/bertopic-turkish-political", embedding_model="sentence-transformers/paraphrase-multilingual-mpnet-base-v2")

topic_model.get_topic_info()

text = "Belediye, sokak hayvanları için yeni bir proje başlattı."
predictions, probabilities = topic_model.transform(text)
```

## Topic overview

* Number of topics: 10
* Number of training documents: 45249

<details>
  <summary>Click here for an overview of all topics.</summary>
  
  | Topic ID | Topic Keywords | Topic Frequency | Label | 
|----------|----------------|-----------------|-------| 
| -1 | türkiye - halk - iktidar - muhalefet - seçmen | 281 | -1_türkiye_halk_iktidar_muhalefet | 
| 0 | türkiye - atatürk - seçmen - siyaset - halk | 20262 | 0_türkiye_atatürk_seçmen_siyaset | 
| 1 | olmak - iktidar - ekonomik - gerekmek - görüş | 12760 | 1_olmak_iktidar_ekonomik_gerekmek | 
| 2 | seçim - seçmen - koalisyon - meclis - ittifak | 3395 | 2_seçim_seçmen_koalisyon_meclis | 
| 3 | medya - milliyet - muhalefet - politik - faşist | 3065 | 3_medya_milliyet_muhalefet_politik | 
| 4 | terör - şiddet - saldırı - terörist - toplum | 2437 | 4_terör_şiddet_saldırı_terörist | 
| 5 | mahkeme - yargı - toplum - kavram - hukuk | 1641 | 5_mahkeme_yargı_toplum_kavram | 
| 6 | seçim - meclis - endişe - sonuç - zor | 648 | 6_seçim_meclis_endişe_sonuç | 
| 7 | köpek - sokak - park - protesto - taksi | 473 | 7_köpek_sokak_park_protesto | 
| 8 | cinsiyet - lgbt - siyaset - cinsel - tecavüz | 287 | 8_cinsiyet_lgbt_siyaset_cinsel |
  
</details>

## Training hyperparameters

* calculate_probabilities: False
* language: None
* low_memory: False
* min_topic_size: 100
* n_gram_range: (1, 1)
* nr_topics: 10
* seed_topic_list: None
* top_n_words: 10
* verbose: False
* zeroshot_min_similarity: 0.7
* zeroshot_topic_list: None

## Framework versions

* Numpy: 1.26.4
* HDBSCAN: 0.8.40
* UMAP: 0.5.7
* Pandas: 2.2.2
* Scikit-Learn: 1.6.1
* Sentence-transformers: 3.3.1
* Transformers: 4.47.1
* Numba: 0.60.0
* Plotly: 5.24.1
* Python: 3.11.11