Generalization of human fear acquisition and extinction within a novel arbitrary stimulus category

Abstract

Adaptive anxiety relies on a balance between the generalization of fear acquisition and fear extinction. Research on fear (extinction) generalization has focused mostly on perceptual similarity, thereby ignoring the importance of conceptual stimulus relations in humans. The present study used a laboratory procedure to create de novo conceptual categories of arbitrary stimuli and investigated fear and extinction generalization among these stimuli. A matching-to-sample task produced two four-member categories of abstract figures. Next, a member from one category was coupled with an aversive electrical stimulation, while a member from the other category was presented alone. As expected, conditioned fear responses generalized to the other members of the first category (skin conductance and online shock-expectancy). Subsequent extinction of the conditioned member also generalized to the other members. However, extinguishing a non-conditioned member failed to reduce fear of the conditioned member itself. We conclude that fears generalize readily across conceptually related stimuli, but that the degree of extinction generalization depends on the stimulus subjected to extinction.

Figure 1. A schematic overview of the experimental phases.

The upper panel represents the trials used in the matching-to-sample training, symmetry test and equivalence test, in order to create two novel stimulus categories (A1-B1-C1-D1 and A2-B2-C2-D2). The first stimulus always represents the sample stimulus, the other three stimuli are the comparison stimuli. The correct comparison stimulus is indicated in bold. The lower panel represents the fear conditioning phase (acquisition, generalization of acquisition test, extinction, generalization of extinction test). The “+”sign indicates that this stimulus is followed by an electric shock in 8 out of 10 trials. The “−”sign indicates that this stimulus is never followed by a shock during those trials.

Figure 2. Abstract figures used in the experiment to create novel categories.

Figure 3. Mean expectancy ratings over de acquisition phase and generalization of acquisition test.

Ratings were registered at the moment the stimulus and expectancy scale disappeared from the screen. Higher levels indicate more certainty about shock (100 =  “Certainly a shock”), lower levels indicate more certainty about absence of shock (0 =  “Certainly no shock”). The left panel represents the data from the acquisition phase, per trial, for both the CS+ (B1) and the CS- (B2). The right panel shows the data from the generalization of acquisition test of all stimuli from both categories. Each stimulus was presented once during this phase.

Figure 4. Mean skin conductance responses over the acquisition phase and generalization of acquisition test.

Responses were range-corrected and square-root transformed. The left panel represents the data from the acquisition phase, per trial, for both the CS+ (B1) and the CS− (B2). The right panel shows the data from the generalization of acquisition test of all stimuli from both categories. Each stimulus was presented once during this phase.

Figure 5. Mean expectancy ratings over the extinction phase and generalization of extinction test.

Ratings were registered at the moment the stimulus and expectancy scale disappeared from the screen. Higher levels indicate more certainty about shock (100 =  “Certainly a shock”), lower levels indicate more certainty about absence of shock (0 =  “Certainly no shock”). The upper graph shows the data of CS-ext group, the lower graph the data of GS-ext group. The left panel represents the data from the extinction phase, per trial, for both B1 and B2 (group CS-ext) or C1 and C2 (group GS-ext). The right panel shows the data from the generalization of extinction test of all stimuli from both categories. Each stimulus was presented once during this phase.

Figure 6. Mean skin conductance responses over the extinction phase and generalization of extinction test.

Responses were range-corrected and square-root transformed. The upper graph shows the data of CS-ext group, the lower graph the data of GS-ext group. The left panel represents the data from the extinction phase, per trial, for both B1 and B2 (group CS-ext) or C1 and C2 (group GS-ext). The right panel shows the data from the generalization of extinction test phase of all stimuli from both categories. Each stimulus was presented once during this phase.