Senticomment is a simple little hacked together script that applies basic sentiment analysis to downloaded YouTube comments. To set up:
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')
- Go to Google Cloud Console and create a new project.
- Enable the YouTube Data API v3.
- Create credentials (OAuth client ID, Application Type: Other) and download them to
client_secrets.json.
Run python3 main.py --videoid={your video ID here} to run the script and generate a CSV file.
python3 main.py --videoid=Zj8h3ZSc-Aw