Installation

Use pip to install this package.

$ pip install --upgrade rgmining-amazon-dataset

Note that this installation will download a big data file from the original web site.

Usage

This package provides module amazon and this module provides function load. The load function takes a graph object which implements the graph interface defined in Review Graph Mining project. The funciton load also takes an optional argument, a list of categories. If this argument is given, only reviews for products which belong to the given categories will be loaded.

For example, the following code constructs a graph object provides the FRAUDAR algorithm, loads the Amazon dataset, runs the algorithm, and then outputs names of anomalous reviewers. Since this dataset consists of huge reviews, loading may take long time.

import fraudar
import amazon

# Construct a graph and load the dataset.
graph = fraudar.ReviewGraph()
amazon.load(graph)

# Run the analyzing algorithm.
graph.update()

# Print names of reviewers who are judged as anomalous.
for r in graph.reviewers:
  if r.anomalous_score == 1:
    print r.name

# The number of reviewers the dataset has: -> 634295.
len(graph.reviewers)

# The number of reviewers judged as anomalous: -> 91.
len([r for r in graph.reviewers if r.anomalous_score == 1])

Note that you may need to install the FRAUDAR algorithm for the Review Mining Project by pip install rgmining-fraudar.

License

This software is released under The GNU General Public License Version 3, see COPYING for more detail.

The authors of the Trip Advisor dataset, which this software imports, requires to cite the following papers when you publish research papers using this package:

• Hongning Wang, Yue Lu, and ChengXiang Zhai, “Latent Aspect Rating Analysis without Aspect Keyword Supervision,” In Proc. of the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’2011), pp.618-626, 2011;

• Hongning Wang, Yue Lu, and Chengxiang Zhai, “Latent Aspect Rating Analysis on Review Text Data: A Rating Regression Approach,” In Proc. of the 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’2010), pp.783-792, 2010.