Help Center
1/6/2024
Cluster analysis or clustering is a series of methods aiming to group a set of objects into subsets, called clusters, so that objects within the same cluster are more similar to each other than to those in other clusters. Since there is no formal definition of similarity, and by extension of a cluster, there is no single method for cluster analysis.
At Polygon, we mainly use cluster analysis in our CM* tool to group ideas according to the frequency with which participants grouped them during the sorting stage. We use a hierarchical method where ideas are integrated into the closest cluster. Using a hierarchical approach allows us to visualize clusters at different levels of granularity, which in turn helps us understand the relationships between ideas during a concept mapping exercise.
For a review of recent methods of cluster analysis, read the article by Ezugwu et el. (2022). For an overview of different approaches, you can consult this guide from sci-kit learn library.
For more information on concept mapping and Polygon’s CM* tool, see the following links: What is concept mapping? and CM*
Concept Mapping Tool
Cluster analysis
