johnafish / senticomment

Gets the sentiment of YouTube comments

Senticomment

Senticomment is a simple little hacked together script that applies basic sentiment analysis to downloaded YouTube comments. To set up:

Installation of Libraries

It's recommended that you use virtualenv so that existing packages aren't tempered with. You'll need Python 3 installed with pip. Run:

pip install httplib2

pip install nltk

pip install csv

pip install google-api-python-client

pip install oauth2client

You'll also need to install vader.

Just go into the python console, import nltk module and use it to download the vader data.

import nltk

nltk.download('vader_lexicon')

Set Up Google Cloud

1. Go to Google Cloud Console and create a new project.
2. Enable the YouTube Data API v3.
3. Create credentials (OAuth client ID, Application Type: Other) and download them to client_secrets.json.

Running the Code

Run python3 main.py --videoid={your video ID here} to run the script and generate a CSV file.

Examples

python3 main.py --videoid=Zj8h3ZSc-Aw

Link to Interactive Histogram as of June 11, 2018

senticomment's Issues

Interactive histogram doesn't work without explicit permission.

I don't know if this is intended, but I assume not :)