Skip to content

Mozzer2310/COMP34711-Deep-Learning

Repository files navigation

Classifying and Clustering Amazon Product Reviews

Clustering (Task 1)

Cluster the top 50 words and the reverse of each of those top 50 words, e.g., half of the occurrences of "canon'' will be transformed into "nonac", in order to test clustering accuracy.

Technologies Used

  • Python & Jupyter Notebook
  • NLTK, scikit-learn, and NumPy

Achievements

  • Clustering Accuracy of 65%-70%
  • Mark 10/13

*For more information see the coursework2-report.pdf section Task 1 (on GitHub)

Classifying

Using the prelabelled corpus build and train a neural network model to classify positive and negative reviews. I created a bi-directional LSTM (Long Short Term Memory) model to solve the task.

Technologies Used

  • Python & Jupyter Notebook
  • NLTK, tenserflow, and NumPy

Achievements

  • Accuracy of 73.4% with a low standard deviation of 0.017
  • Mark 12/12

*For more information see the coursework2-report.pdf section Task 2 (on GitHub)

About

Repository for NLP coursework 2

Resources

Stars

Watchers

Forks