Skip to content
Javier Sanz-Cruzado edited this page Jan 23, 2020 · 2 revisions

Description

The EWC1 program compares the nDCG values of several algorithms depending on whether the weights of the links are used to generate the recommendation or not (i.e. if the frequencies for the IR algorithms are binary or not). This program can be used to generate Figure 1(a).

Execution

The command to execute this program is the following:

java -jar contact-rec-axioms.jar ewc1 train test algorithmsFile outputDirectory directed recLength printRecs

where

  • train: is the file containing the training graph.
  • test: is the file containing the test edges.
  • algorithmsFile: is the XML file containing the algorithms to compare (see conf. files)
  • outputDirectory a directory where to store the recommendations and the comparison file.
  • directed: true if the graph is directed, false otherwise.
  • recLength: the maximum number of recommended people for each target user (in our experiments, 10)
  • printRecs: true if we want to store the recommendations, false if we just want the comparison file.

Outcome

After execution, if the printRecs option is set to true, the output directory will contain two subdirectories: one called weighted which will contain the all the recommendations taking the weights of the links into account, and another called unweighted which will contain the recommenders when weights are not considered. The base folder will have a ewc1.txt file showing the comparison between the weighted and unweighted variants.

Clone this wiki locally