Skip to content

An Application which can be used to feed speech transcript via a chatbot interface and get the depression indicator of the person speaking. A deep learning model is used to classify the depression percentage

License

Notifications You must be signed in to change notification settings

boylerplet/Depression-Detector

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Readme

This project contains an application to take input of text and classify it into two categories which are Depressed or Non-Depresssed using a deep learning algorithm. The project contains a frontend where the user can input text data which will be sent to the model to be processed and a result will be generated. The implementation has two components the front-end for user interaction and the back-end for the python run flask server

Pre-requisites

This project uses a deep learning algorithm word vectorization using the GloVe vector corpus which has to be pre-downloaded by the user
It is available to download Here

It must be extracted into the folder glove.6B and the folder should be placed in the server directory

The final path must look something like this server\glove.6B\*.txt

Execution

Run Front-end

  • Open a command line in the client directory
  • npm install --legacy-peer-deps to install all the required node libraries
  • npm start to run the development server

Run Flask Server

The backend part of the depression training model

  • pip install virtualenv to install virtual environment to local machine
  • Open the server directory in a new command line
  • Create a virtual environment in current directory with virtualenv venv
  • Switch to the virtual environment venv\Scripts\activate
  • Install all the required python Libraries pip install -r requirements.txt
  • Run the flask development server using flask run

xcopy <source> <destination> /EXCLUDE:exclude.txt /S

/S is for recursive copy

About

An Application which can be used to feed speech transcript via a chatbot interface and get the depression indicator of the person speaking. A deep learning model is used to classify the depression percentage

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published