Sadness facilitates “deeper” reading comprehension: a behavioural and eye tracking study

ABSTRACTReading is one of the most common everyday activities, yet research elucidating how affective influence reading processes and outcomes is sparse with inconsistent results. To investigate this question, we randomly assigned participants (N = 136) to happiness (positive affect), sadness (negative affect), and neutral video-induction conditions prior to engaging in self-paced reading of a long, complex science text. Participants completed assessments targeting multiple levels of comprehension (e.g. recognising factual information, integrating different textual components, and open-ended responses of concepts from memory) after reading and after a week-long delay. Results indicated that the Sadness (vs. Happiness) condition had higher comprehension scores, with the largest effects emerging for assessments targeting deeper levels comprehension immediately after reading. Eye-tracking analyses revealed that such benefits may be partly driven by sustained attentional focus over the 20-minute reading session. We discuss results with respect to theories on affect, cognition, and text comprehension.KEYWORDS: reading comprehensioneye-trackingnegative affecttext processing Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1 We began with maximal random effects structures, but simplified them to address convergence issues. For the manipulations checks and learning measures models, we began with (Condition | Cohort). Our initial models for the reading time and eye-gaze measures included the following structure: (Page number | Participant: Cohort) + (Condition * Page number | Cohort).2 Regarding the results of the models with and without reading time as a covariate, we found that the results were the same with one minor exception. Specifically, whereas the difference between the positive and neutral slopes for the proportion of regressive fixations yielded a p = .07 with reading time in the model, this difference changed to p = .058 without reading time included.3 Two of the models, reading time and fixation duration, did not converge with (1 | Cohort) included. We thus re-ran the models without Cohort as a random intercept, and the results did not change.Additional informationFundingThis research was supported by the National Science Foundation (NSF) (DRL 1235958, DRL 1920510). Any opinions, findings and conclusions, or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of NSF.