Skip to content

Ritchieluk/Brain.Dump

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

132 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Build Status

Brain.Dump UI

A Sentiment Analysis tool made to translate journal entries into meaningful representations of the emotion within the entries.


By:

  • Luke Ritchie

Disclaimer

This repository used to house a Django application, this was the old version of the application. It has since been split into 3 components and is being rebuilt. To find that application, you can go here: https://github.com/Ritchieluk/OldBrainDump

Components

Brain.Dump can be split into three major components: a journaling site that can create animate journals, a reinforcement-learned algorithm that acts as an interpreter for analyzing the entries, and an api to communicate between the components and database.

The Journal


The Journal will be a website allowing you to write and save a journal entry, and then submit once you have finished writing it. Upon submission it will be sent to the interpreter to be analyzed. Emotionally charged words will be picked up by the Interpreter. The Interpreter will send back a JSON containing the information required by the Journal to animate it and create an image.

You can find examples of this animation here:

The Interpreter


The Interpreter is a reinforcement-learned sentiment analysis tool that will read the journal entries and return decimal values for different percentages of certain emotions, which will then be passed on to the Drawer.

The API


The API is a Flask application that handles communication between the Journal, the Interpreter, and the Database. A link to that project can be found here: https://github.com/Ritchieluk/BrainDumpAPI

Future Goals


We envision many future applications for such a program.

  • The machine learning tool could be reinforced by actual analyzation data from psychologists and psychiatrists, and be used to flag entries potentially indicative of mental illness
  • Users could view summaries of their journal entries via most used words, most present emotion, graphs of emotional changes, most common themes, etc.
  • This machine learning instance could be used on more than just braindumps, the braindump journaling platform could expand to blogs, message boards, forums, each of which would have icons indicative of the emotional content within.
  • There could be multiple styles of artful icons that users could choose between
  • The main site page could be an image of the summarized emotional content of all recent posts, to create a snapshot of the recent mindset of its users
  • Users of the site could search through posts and entries via tag words and view user opinions on the site via summarized emotional content of all entries relevant to the tag word(s).
  • Users could feed the ML instance pre-written content to be analyzed and represented

Project setup

npm install

Compiles and hot-reloads for development

npm run serve

Compiles and minifies for production

npm run build

Run your tests

npm run test

Lints and fixes files

npm run lint

Customize configuration

See Configuration Reference.

About

A Sentiment Analysis tool made to translate journal entries into meaningful representations of the emotion within the entries.

Resources

Stars

2 stars

Watchers

2 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors