Exploratory Study into Relations between Cognitive Distortions and Emotional Appraisals

TL;DR

The paper addresses how cognitive distortions relate to emotional appraisal dimensions by building an appraisal predictor trained on Crowd-enVent and applying it to the Thinking Trap dataset to analyze distortion–appraisal relations. It demonstrates statistically significant distortion–appraisal associations, characterizes distortion-specific appraisal profiles relative to a no-distortion baseline, and shows that cognitive reframing induces a positive shift in appraisal dimensions. The findings support a link between distortions and appraisals and suggest that integrating these constructs can enhance automated emotion regulation in NLP systems, while also noting data quality and ethical considerations. Overall, the work lays groundwork for interdisciplinary study at the intersection of cognitive distortions, emotional appraisal, and cognitive reframing, with methodological and practical implications for future research and applications.

Abstract

In recent years, there has been growing interest in studying cognitive distortions and emotional appraisals from both computational and psychological perspectives. Despite considerable similarities between emotional reappraisal and cognitive reframing as emotion regulation techniques, these concepts have largely been examined in isolation. This research explores the relationship between cognitive distortions and emotional appraisal dimensions, examining their potential connections and relevance for future interdisciplinary studies. Under this pretext, we conduct an exploratory computational study, aimed at investigating the relationship between cognitive distortion and emotional appraisals. We show that the patterns of statistically significant relationships between cognitive distortions and appraisal dimensions vary across different distortion categories, giving rise to distinct appraisal profiles for individual distortion classes. Additionally, we analyze the impact of cognitive restructuring on appraisal dimensions, exemplifying the emotion regulation aspect of cognitive restructuring.

Figures (8)

• Figure 1: Overview of the appraisal prediction model.
• Figure 2: Appraisal ratings prediction accuracy in RMSE for our model, the results reported by troiano-etal-2023-dimensional, and those calculated against median predictions for each appraisal dimension as baseline.
• Figure 3: Discretized significance plots of distortion-appraisal pairs for two definitions of the negative groups. White cell implies a statistically significant relation between the distortion-appraisal pair, the black cell represents no statistically significant difference.
• Figure 4: Baseline appraisal profile associated with the "no distortion" class.
• Figure 5: Appraisal profiles (relative to the "no distortion" baseline) for all distortion classes. The x-axis represents different appraisal dimensions considered while the y-axis plots the difference in appraisal scores between individual distortions and the baseline ($score(distortion) - score(baseline)$).