Generalizing About Striking Properties: Do Glippets Love to Play With Fire?

Abstract

Two experiments investigated whether 4- and 5-year-old children are sensitive to whether the content of a generalization is about a salient or noteworthy property (henceforth “striking”) and whether varying the number of exceptions has any effect on children’s willingness to extend a property after having heard a generalization. Moreover, they investigated how the content of a generalization interacts with exception tolerance. Adult data were collected for comparison. We used generalizations to describe novel kinds (e.g., “glippets”) that had either a neutral (e.g., “play with toys”) or a striking property (e.g., “play with fire”) and measured how willing participants were to extend the property to a new instance of the novel kind. Experiment 1 demonstrated that both adults and children show sensitivity to strikingness in that striking properties were extended less than neutral ones, although children extended less than adults overall. The responses of both age groups were significantly different from chance. Experiment 2 introduced varying numbers of exceptions to the generalization made (minimal: 1 exception; maximal: 3 exceptions). Both adults and children extended both types of properties even in the face of exceptions, but to a lower degree than in Experiment 1. Striking properties were extended less than neutral ones, as in Experiment 1. We observed that the greater the number of exceptions, the lower the rates of extension we obtained, for both types of properties in adults, but only with striking properties in children. Children seemed to keep track of varying numbers of exceptions for striking properties, but their performance did not differ from chance. The findings underscore that 4- and 5-year-old children are sensitive to strikingness and to exception tolerance for generalizations and are developing toward an adult-like behavior with respect to the interplay between strikingness and exception tolerance when they learn about novel kinds. We discuss the implications of these results with regards to how children make generalizations.

Generic Language for Social and Animal Kinds: An Examination of the Asymmetry Between Acceptance and Inferences

“…However, our findings do not support this prediction, as we found no differ-ence in the generics' acceptance conditions linked to property valence. Furthermore, whereas Cimpian et al (2010) reported no variation in prevalence estimations as a function of property valence, we found that neutral generics yielded higher levels of implied prevalence than dangerous generics, consistent with previous evidence (Lazaridou-Chatzigoga et al, 2019;Prasada et al, 2013).…”

“…This possibility is also consistent with previous evidence showing that dangerous generic properties, compared to other generic properties, were interpreted as referring to common dispositions (i.e., properties that Ks are commonly disposed to have but are displayed only under certain circumstances) rather than prevalent properties (i.e., properties actually displayed by a high proportion of Ks; Prasada et al., 2013 ), potentially leading to the expectation that the relevant property is less generalizable (Lazaridou‐Chatzigoga et al., 2019 ). Thus, this seems to be the most plausible explanation for this result.…”

“…Similarly, Lazaridou-Chatzigoga, Katsos, and Stockall (2019) found that both adults and children were more willing to extend the properties ascribed by neutral generic properties about novel creatures (e.g., "Ackles love to play with toys") to a new member of the category than the properties ascribed by dangerous generic properties (e.g., "Ackles love to play with fire"). However, as Lazaridou-Chatzigoga et al (2019) noted, the properties they tested were more child-friendly than those of Cimpian et al (2010) and thus potentially less salient. Moreover, many of their dangerous properties were likely to be perceived as dangerous for the category members only.…”

“…However, as Lazaridou‐Chatzigoga et al. ( 2019 ) noted, the properties they tested were more child‐friendly than those of Cimpian et al. ( 2010 ) and thus potentially less salient.…”

“…Such statements led to lower prevalence estimates than other generic properties. Similarly, Lazaridou‐Chatzigoga, Katsos, and Stockall ( 2019 ) found that both adults and children were more willing to extend the properties ascribed by neutral generic properties about novel creatures (e.g., “Ackles love to play with toys”) to a new member of the category than the properties ascribed by dangerous generic properties (e.g., “Ackles love to play with fire”). However, as Lazaridou‐Chatzigoga et al.…”