synthetic package¶

Provides a method to load a synthetic review dataset.

The synthetic review dataset has been introduced in the paper [1] published in the 22nd International Conference on Database and Expert Systems Applications.

The number of anomalous reviewers this dataset has is defined in ANOMALOUS_REVIEWER_SIZE, and each anomalous reviewer has anomaly in theirname.

This package provides a metho load, which is an alias of synthetic.loader.load(). The method takes a graph instance and adds reviewers, products, and reviews to the graph.

References

[1]

Kazuki Tawaramoto, Junpei Kawamoto, Yasuhito Asano, and Masatoshi Yoshikawa, “A Bipartite Graph Model and Mutually Reinforcing Analysis for Review Sites,” Proc. of the 22nd International Conference on Database and Expert Systems Applications (DEXA 2011), pp.341-348, Toulouse, France, August 31, 2011. (Acceptance rate 25%)

synthetic.ANOMALOUS_REVIEWER_SIZE = 57¶: The number of anomalous reviewers in this synthetic dataset.

Submodules¶

synthetic.loader module¶

Provide a loading method of synthetic dataset.

synthetic.loader.load(g)[source]¶

Load synthetic dataset.

Parameters:	g – an instance of bipartite graph.
Returns:	The graph instance g.