Skip to content

This project has the aim to define a Sentiment Analysis on Yelp Dataset for review data classification. Furthermore, we make a fake review model using mainly python ML libraries.

License

Notifications You must be signed in to change notification settings

kode-git/yelp-sa

Repository files navigation

Sentiment Analysis on Yelp Reviews

alternatetext alternatetext alternatetext alternatetext alternatetext

This project has the aim to define a Sentiment Analysis on Yelp Dataset for review data classification. Furthermore, we make a fake review model using mainly python ML libraries.

Summaries

  1. Introduction: It is dedicated to an introduction on the problem instance and general description of the notebook contents
  2. Loading Dataset: Description on how we loaded information on the pandas dataframe
  3. Data Analysis: Analysis on the data types and values distribution in the entire dataset
  4. Data Pre-processing: Manipulation of information to prepare data for model input
  5. Data modelling: Building and training of models
  6. Data results: Shows results on training phase and final metrics
  7. Conclusions: Final observations

Dependencies

We produces a requirement.txt to use in the setting that should mantain dependencies consistency between different deployment. If you try to deploy it and have some dependencies problem; please, open an issue in the repository.

Modelling description

Models are some samples about evaluation on some techniques in relation to the Yelp dataset. In other words, we can define a better model using some state-of-art architectures like Convolutional LSTM, biLSTM or some of their variation. These models are in the version 2 which evaluates performance in relations to the old ones.

Author

  • Mario Sessa (@kode-git)

About

This project has the aim to define a Sentiment Analysis on Yelp Dataset for review data classification. Furthermore, we make a fake review model using mainly python ML libraries.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published