reviews.py uses the IMDB file as the data set. The code implements several different machine learning algorithms, but I encourage you to try it out for yourself to narrow down which models you prefer. In general, I recommend using the Support Vector Classifier, Stochastic Gradient Descent, Nearest Centroid and Logistic Regression. All parameters have been fine tuned using GridSearchCV, but once again I encourage you to try to make it more accurate using other tests.
-
Notifications
You must be signed in to change notification settings - Fork 0
dhruvmk/sentiment_classifier
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This project contains the required code and data set to build a very accurate (92%+) sentiment classifier that can tell if a movie review is positive or negative.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published