What I Like About You!

Well, what we like about wargaming, that is.

In the Great Wargaming Survey, 2025 edition, one survey question asked respondents, “What do you like most about miniatures wargaming?” Responses were collected as unstructured text (up to about 2,100 characters per response and anything goes!) allowing participants to write without constraint to include all of the facets of wargaming that they like.  In total, there were 4,063 non-blank responses recorded.  I last looked at this question in GWS 2023.  I wonder if wargamers' "likes" have changed since then?

To parse and interpret this large body of text, machine learning techniques are introduced.  Specifically, a variety of cluster analysis techniques are applied to the survey data.  These statistical methods help uncover underlying data associations and reduce thousands of unique words (tokens) to a smaller dataset.  The aim of this data reduction step is to transform unstructured text into a manageable set of representative tokens while preserving essential meaning.

After routine preprocessing and tokenization, the dataset produced 2,719 unique terms with associated frequencies.  A further data step involved removing near-zero variance terms thereby reducing this set dramatically to just nineteen key word tokens.  These nineteen tokens are:

games, people, painting, miniatures, history, research, collect, model, terrain, table, fun, creative, army, build, aspect, good, time, hobby, like.

The last five tokens in the list of "aspect", "good", "time", "hobby", and "like" were excluded from analysis as either too general or redundant. 

With the dataset reduced from over 4,000 terms to fourteen, cluster analysis provides the next layer of insight.  The resulting dendrogram (see Figure 1) reveals a clear and intuitive structure that I break down layer by layer. 

Figure 1

The dendrogram organizes the “most liked” aspects of wargaming by how closely respondents associate the tokens.  Joining at a lower height in the dendrogram indicates a stronger relative relationship with higher splits indicating more separation.

At the highest level, "games" stands apart from all other terms, joining the rest of the terms only at a relatively large distance. This indicates that respondents view gaming as distinct reinforces the notion that gaming, itself, is the central facet of the hobby.  From the dendrogram (see Figure 2), "games" is not intertwined with the other activities. 

Figure 2

The next major split separates "people" from the remaining terms (see Figure 3). Together, this creates a clear hierarchy in a three-cluster solution of:

• Games (most distinct)
• People (second most distinct)
• Everything else (more tightly interrelated)

Results suggest that gaming and social interaction are the two most independently valued aspects of wargaming.

Figure 3

Below this top structure in the hierarchy, several distinct clusters emerge from the dendrogram analysis (see Figure 4).

Figure 4

"Painting" and "miniatures" form one tight pairing.  This closeness suggests a connection between painting and the objects being painted.  "Collect" and "research" also pair closely.  Their proximity suggests that painting and amassing armies of figures and learning about them seemingly go hand-in-hand.  "Table" and "terrain" form another very tight cluster representing the physical environment of play.  These pairings are intuitive and reinforce the notion that respondents think in terms of hobby activities rather than isolated concepts.

Slicing across the dendrogram at a practical level (around mid-height) yields four meaningful groupings (see Figure 5):

• Games (standalone)
• People (standalone)
• Painting/miniatures (craft-focused sub-cluster)
• All remaining hobby activities (a blended cluster of building, modeling, and researching)

Figure 5

Interestingly, "creative" sits between "history" and all of the craft elements in Cluster 4.  In this hierarchy, creativity acts as a bridge linking both building and interpreting history.

What can we infer from this analysis of survey respondents' likes about wargaming?

To begin, analysis supports the notion that gaming, social interaction, and painting emerge as primary drivers.  All other activities form a supporting ecosystem.  Analysis also suggests a structure to the wargaming hierarchy.  That is, wargaming should not be viewed as a single, unified, activity but as a combination of semi-independent domains.  If we return to the three-cluster solution, the clusters are:

• Gaming is central but conceptually separate.
• Social interaction is nearly as important and also distinct.
• Everything else forms an interconnected hobby engine of crafting, researching, and building.

The dendrogram shows that these are all part of the same hobby.  The distinction is that participants mentally separate playing and socializing from the preparatory and creative work.  Overall, results reinforce the idea that miniatures wargaming is a layered hobby with distinct, varied but interconnected facets of engagement.

For the cluster analysis, itself, these classifications demonstrate how a large and unstructured dataset can be reduced into a smaller number of meaningful dimensions without losing interpretive power.  Now, I mentioned that I examined this question in the 2023 survey.  Have "likes" changed in the two years having a different survey population and the ability to respond in unstructured text?

Figure 6 shows that hierarchy and association of the best aspects of wargaming have not changed all that much! 

Figure 6

The four-cluster solution in GWS 2023 mirrors that of the GWS 2025 four-cluster solution with the same clusters of,

• Games (standalone)
• People (standalone)
• Painting/miniatures (craft-focused sub-cluster)
• All remaining hobby activities (a blended cluster of building, modeling, and researching)

Remarkable.  The same question asked two years apart produces a very similar profile of wargamer favored aspects of the hobby even when survey respondents can enter anything they please.  Another tick alongside the scoring of the reliability of data.  Fascinating.