metadata
title: README
emoji: 📚
colorFrom: purple
colorTo: green
sdk: static
pinned: false
Yapılan proje adımları aşağıda yer almaktadır.
The steps to create this dataset are as follows.
Step 1: Data Scraping Tool: https://github.com/Teknofest-Nane-Limon/twitter-scraper
Step 2: Data Labeling Tool: https://github.com/Teknofest-Nane-Limon/easy-data-labeling-engine
- Productization of labeled data: https://huggingface.co/datasets/nanelimon/turkish-social-media-bullying-dataset
Step 3: Data Cleaning Tool: https://github.com/Teknofest-Nane-Limon/text-data-cleaner
Step 4: Data Modeling:
- 4.1. Analysis and trials notebook for TFID: https://github.com/Teknofest-Nane-Limon/tfidf-model-turkish-bullying
- 4.2 Analysis and essays notebook for Bert Mobel: https://github.com/Teknofest-Nane-Limon/bert-base-turkish-bullying/blob/main/bert-cv.ipynb%20-%20Colaboratory.pdf & bert-cv.ipynb
- 4.3 Modeling notebook with hyper parameters from Bert Model: https://github.com/Teknofest-Nane-Limon/bert-base-turkish-bullying/blob/main/bert-base-turkish-bullying-best-parameter.ipynb
Step 5: Productization of the Model:
- 5.1 Python FastAPI: https://github.com/Teknofest-Nane-Limon/turkish-bullying-api
- 5.2 Hugging Face : https://huggingface.co/nanelimon/bert-base-turkish-bullying
For Example
Cinsiyetçilik Örneği:
Irkçılık Örneği:
Kızdırma Örneği:
Nötr Örneği
