Skip to content
This repository has been archived by the owner on Feb 21, 2024. It is now read-only.

๐Ÿš€ Cyberbullying Detection API: Safeguarding the Digital Realm ๐Ÿ›ก๏ธ

Notifications You must be signed in to change notification settings

notcoderguy/cyberbullying-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

10 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

Cyberbullying Detection API

!! ARCHIVE !!

This repo is a public archive now, further development will be done on new repo nirodh.

Overview

The Cyberbullying Detection API is a fast and efficient tool for detecting instances of cyberbullying in text. It provides a simple endpoint /analyse where you can submit text, and it will respond with a classification indicating whether cyberbullying is detected and the type of cyberbullying if applicable.

Table of Contents

Endpoint

/analyse

This is the main endpoint of the API for analyzing text data for cyberbullying. Users can post a JSON object with the text they want to analyze.

HTTP Method: POST

Request Format:

{
    "text": "Women are meant in kitchen."
}

Response Format:

{
    "status": 1,
    "message": "Cyberbullying on the basis of gender is detected.",
    "label": "gender"
}

How to Use

  1. Clone the Repository:
git clone <repository-url>
  1. Install Dependencies:
pip install -r requirements.txt
  1. Run the API:
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
  1. Make POST Requests:

Response

The API response will contain the following fields:

  • status: An integer indicating the status of the analysis. 1 indicates cyberbullying is detected, 0 means no cyberbullying is detected.
  • message: A message describing the analysis result.
  • label: If cyberbullying is detected, this field specifies the type of cyberbullying detected.

Planned Roadmap

  • Data Logging and Feedback Mechanism: Implement a data logging system and a feedback mechanism to collect user-generated data and feedback for model refinement (as discussed earlier).

  • Image Analysis: Extend the API to support image analysis for detecting cyberbullying in images. Users should be able to submit images for analysis.

  • Multilingual Support: Add support for multiple languages to make the API more versatile and accessible.

  • User Authentication: Implement user authentication to track and analyze usage patterns, which can help improve the service over time.

  • Model Fine-tuning: Continuously update and fine-tune the model with new data to enhance its accuracy and effectiveness.

  • Documentation: Expand and improve the API documentation to make it more user-friendly and informative.

  • Scalability: Ensure the API can handle a growing number of requests by optimizing its performance and potentially deploying it on a scalable infrastructure.