Perceptions of Brain Training: Public Expectations of Cognitive Benefits From Popular Activities

Abstract

Many popular activities are thought by the general public to improve cognitive function. Such expectations can influence how often people engage in these activities, as well as the scientific evaluation of their putative cognitive benefits, e.g., via placebo effects. Here, we gathered survey data about the public's perceptions of nine different activities commonly thought to be cognitively stimulating, including "brain-training" games. Information was collected about the degree to which participants thought each activity was beneficial for improving cognitive function and how often they engaged in each activity. The patterns of correlation between ratings reveal details about the perception of cognitive benefits and its relation to engagement. They suggest that participants varied with respect to an overarching perception of the entire set of activities, which were perceived also as divided into three clusters. Frequency of engagement and perceived cognitive benefits were positively correlated across participants for each activity considered individually. But, when the activities were compared, the magnitude of their perceived benefits was not a good predictor of their frequency of engagement (and vice versa). Though small, there were systematic demographic differences. Women were more optimistic than men about cognitive benefits. Individual participants differed in the range of their ratings of benefit across activities, and these ranges were greater for younger than older participants, suggesting that perceptions of benefit are more differentiated among the young. Besides contributing to a better understanding of public expectations of cognitive benefits, the findings of this study are relevant to the critical evaluation of such benefits. Our survey can be viewed as providing an interface between expectations held by the general public and the design of studies examining the efficacy of cognitive training. The type of information it provides could be used in the selection of activities performed by an active control group, so that control activities match the treatment intervention as closely as possible with respect to such expectations.

Keywords: active control group; cognitive training; engagement; expectation; growth mindset; neuroplasticity; placebo effect; video games.

Figure 1

Survey questions on frequency of engagement and cognitive benefit. Shown beneath each question are the nine rated activities and labels for points on the five-point rating scales.

Figure 2

Ratings of activities on (A) perceived cognitive benefits and (B) frequency of engagement. Each panel shows stacked bar graphs of the nine activities, which are ordered by the total number of responses in the top two categories of the five-point rating scale.

Figure 3

Correlations between ratings of activities on perceived cognitive benefits and frequency of engagement. Spearman’s correlations are shown, both numerically and as heat maps. Those for perceived benefit between different activities and engagement between different activities are shown respectively in Panels (A,B). Panel (C) shows the correlations between perceived benefits and engagement, both for the same activity (main diagonal) and for two different activities (off main diagonal). Statistically significant correlations, with probabilities below a 0.05 criterion adjusted for multiple tests with the Benjamini-Hochberg Procedure, are shown in bold print.

Figure 4

Dendrogram displaying similarity in the perceived cognitive benefits of the nine activities. The similarity of each pair of activities is based on the correlation between their respective ratings of cognitive benefits across participants. The taxonomic structure of the entire set of activities was obtained from these pairwise correlations using a hierarchical clustering algorithm (hclust function, Spearman method, R statistical package). The dashed line shows the level of the hierarchy containing the groups visually apparent in the correlation matrix (Figure 3A).

Figure 5

Parameters of rating distributions from individual participants. Each distribution consisted of the nine ratings of cognitive benefits, one for each activity, by a single participant. The parameters are the (A) median, (B) range, and (C) skew of these distributions. The histograms displayed in the figure show how these parameters, which were obtained for each individual participant, were distributed across the entire set of participants. See the text for further details.