GitHub - csko/Youtube-classifier

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 21 Commits
db		db
readability		readability
README		README
dict_vectorizer.py		dict_vectorizer.py
features.py		features.py
parse.py		parse.py
save_dv.py		save_dv.py

Repository files navigation

Youtube comment classifier

Classifies comments as spam or adult content using machine learning tools.

Used tools:
 - python2
   - sklearn
   - numpy
   - nltk
   - pyyaml

Used data:
A set of youtube comments annotated by the Alois Zistler and Mark Guelbahar (Institut fur Rundfunktechnik).