SciQS

This page is devoted to show the supplementary materials for the paper entitled "A contrast pattern-based scientometric study of the QS world university ranking" published in IEEE Access, 2020.

Classification results obtained by all the tested classifiers

Classification results by using accuracy as evaluation measure ->

Our collected database.

Database including the name of the universities and their positions into the QS ranking [1] ->
Database without including the position ->
Database without including the name of the universities ->

HTML models for visualizing patterns with up five items

HTML models by using Bokeh [2] (they are interactive) ->

Extracted contrast patterns

All extracted patterns describing our collected database and the problem's classes by using the HRFm algorithm [3] ->
Most used features from the set of extracted patterns ->
Most used items from the set of extracted patterns ->

References

[1] QS Ranking. URL https://www.topuniversities.com/university-rankings

[2] Bokeh Development Team (2019). Bokeh: Python library for interactive visualization. URL https://bokeh.org

3] Loyola-González, O. et al. (2017). PBC4cip: A new contrast pattern-based classifier for class imbalance problems. Knowledge-Based Systems, 115, 100–109. http://doi.org/10.1016/j.knosys.2016.10.018.