Skip to content

Used the official data from a startup(Niki.ai) to predict the sentiment of feedback the company received for its chatbot.

License

Notifications You must be signed in to change notification settings

AneeshBose/5-class-sentiment-analyzer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

README File

Step 1: Run pip install -r requirements.txt to install all the dependencies to run the source python file

Step 2: Navigate to the src folder and run the Niki.ai_Assignment_Part1.py file

  • An 80:20 train:test split cross-validation was done to train the model
  • Used a RandomForestClassifier to classify the different classes, which in this case are the Star Ratings. By using this algorithm, one need not normalize the data.
  • Used Tf-Idf Vectorizer to build the feature vector consisting of important words

About

Used the official data from a startup(Niki.ai) to predict the sentiment of feedback the company received for its chatbot.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published