A social media platform that you can trust.
Explore the docs »

Report Bug · Request Feature

Key Contributors: Gaurav Agrawal, Shrid Pant and Tarun Dhankhar.

Table of Contents


Cyber bullying has risen exponentially over the years, especially among teens. And while the traumatic experiences of the victims are well-known, little has been done by social media giants to preemptively take action. On a large scale application, merely acting on reported posts is not nearly sufficient. It is absolutely necessary to proactively participate in the prevention of cyber bullying.

About The Project

Mindhunters is a state-of-the-art LSTM-based NLP-algorithm on which this social media platform is wrapped. It provides sophisticated detection of texts that are violent, offensive, sexist, racist, discriminant or derogatory in nature. Scores are generated using Mindhunters, which affect the reputation of each user. The generated scores are used to provide alerts to the social media platform, which may take appropriate action against the post and/or user.

Built With

The server-side application was built with Flask, Keras and NLTK. Other resources included SQLite3 for database management, and HTML, CSS and JavaScript for the client-side application. Mindhunters was made possible by many open-sourced libraries and frameworks.


Each post a user posts has a score associated with it. The score is given by the sigmoid function of the output layer of NLP model. If the value of score is greater than 0.5 the post is considered to be voilent and the reputation value is decreased according to a simple formula, vice versa if the score is less than 0.5. The reputation score helps us in determining the frequency of voilent posts that a user posts on social media.


The social media platform is a web application monitored by Mindhunters to provide safety from cyber bullying. To execute, simply:

  1. Clone this repository with git clone https://github.com/shridpant/mindhunters. Please ensure that you have all the dependencies from requirements.txt installed.
  2. Start your server with python app.py.
  3. Open the address from your terminal on your browser. And you're all set!


This project welcomes contributions and suggestions. Feel free to fork this repository or submit your ideas through issues.


Distributed under the MIT License. See LICENSE for more information.


The entire Mindhunters application was built by Gaurav Agrawal, Shrid Pant and Tarun Dhankhar. Please feel free to contact any of us to discuss the project!

Future Works

We plan to extend the Mindhunters algorithm to include images, audios and videos. In text-based analysis, Mindhunter can be extended to the identification of misinformation ("fake news").


Mindhunters wouldn't be possible without the following resources:

Built With

Share this project: