https://github.com/aayush210789/Deception-Detection-on-Amazon-reviews-dataset

A SVM model that classifies the reviews as real or fake. Used both the review text and the additional features contained in the data set to build a model that predicted with over 85% accuracy without using any deep learning techniques.
https://github.com/aayush210789/Deception-Detection-on-Amazon-reviews-dataset

nlp-machine-learning nltk sklearn svm visualization

Last synced: 14 days ago
JSON representation

A SVM model that classifies the reviews as real or fake. Used both the review text and the additional features contained in the data set to build a model that predicted with over 85% accuracy without using any deep learning techniques.

• Host: GitHub
• URL: https://github.com/aayush210789/Deception-Detection-on-Amazon-reviews-dataset
• Owner: aayush210789
• Created: 2018-02-14T00:07:28.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-03-20T16:15:14.000Z (over 6 years ago)
• Last Synced: 2024-08-01T16:50:38.066Z (3 months ago)
• Topics: nlp-machine-learning, nltk, sklearn, svm, visualization
• Language: Jupyter Notebook
• Size: 5.27 MB
• Stars: 51
• Watchers: 3
• Forks: 26
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Deception-Detection-on-Amazon-reviews-dataset

A SVM model that classifies the reviews as real or fake. Used both the review text and the additional features contained in the data set to build a model that predicted with over 90% accuracy without using any deep learning techniques. 

NLTK and Sklearn python libraries used to pre-process the data and implement cross-validation.

Worked with a recently released corpus of Amazon reviews 

Finally, did an exploratory analysis on the dataset using seaborn and Matplotlib to explore some of the linguistic and stylistic traits of the reviews and compared the two classes.