The similarity matrix helps you identify strong card pairings and potential groupings in open and hybrid card sorts.
The matrix shows the percentage of participants who grouped two cards together and visually clusters the most closely related pairings along the right edge of the triangular matrix with darker colors indicating higher agreement among participants.
Understanding the Similarity Matrix
The similarity matrix is useful to quickly identify how each card stands among other cards, and define clusters that are grouped together or likely belong in the same section.
On the other hand, you can rule out unlikely groupings for cards that show low agreement rate.
In the example below, 100% of participants (4 out of 4) placed Transportation and Travel Companions in the same category.
You can examine the matrix at a higher level to locate clusters as shown above: Transportation x Travel Companions x Travel Destination x Accommodations were all placed together in the same category with 100% agreement rate.
You can pair the analysis with the agreement matrix to see how these cards are similarly categorized.
To learn more about agree matrices, see the article on understanding the agreement matrix.