Lars Höft

Background: Argumentative writing is a key competence for academic success. Feedback can foster competence development, yet the associated outcomes show considerable heterogeneity among students. Students’ achievement goals and argumentative writing skills moderate the effectiveness of feedback in classroom settings. However, it is unclear whether these individual differences explain variations in feedback effects within AI-supported classroom contexts.Objective: We examine individual differences in the effectiveness of AI feedback on argumentative writing performance by assessing how the feedback condition (AI feedback versus generic revision prompt) interacts with students’ achievement goals (mastery, performance-approach, and performance-avoidance) and their argumentative writing skill to predict text revision quality.Method: In a classroom-based experiment, secondary school students (N = 805) wrote and revised argumentative texts. Students were randomly assigned to receive either immediate, individualized AI feedback or a generic revision prompt. The quality of the revised argumentative text was the outcome variable.Results: Mastery goal orientation moderated feedback effects. The benefit of AI feedback compared to the revision prompt was highest for students with low mastery goals. Furthermore, argumentative writing skill moderated the interaction between performance-approach goals and the feedback condition in a three-way interaction. For students with higher baseline argumentative writing skill, the benefit of AI feedback on revision quality was positively associated with a stronger performance-approach. Conversely, for students with lower baseline skills, a stronger performance-approach orientation was associated with higher revision quality in the control condition than in the AI feedback condition.Conclusion: AI feedback effects on text revision quality are conditional. Explaining differences in its effectiveness requires the simultaneous consideration of feedback conditions, students’ achievement goals, and their baseline argumentative writing skills.

Conscientiousness and interest each have a substantial impact on learning. The conscientiousness × interest compensation (CONIC) model (Trautwein et al., 2015) describes their interplay as compensatory in predicting academic effort and achievement. The CONIC model has been applied to aggregated effort and achievement measures, but more fine-grained insights on the task level are missing. We investigated whether the compensatory relationship between conscientiousness and interest holds on the task level. Therefore, we examined the interplay of students’ conscientiousness and their subject interest (in German, chemistry, mathematics, and physics) as well as situational interest in the task at hand when predicting effort and achievement in an argumentative writing task. Our sample comprised 1,839 secondary school students (Mage = 16.4, SD = 1.5, 42.7% female) in Germany. Students worked on two argumentative texts and filled in questionnaires. The latent moderated structural equations method was applied to investigate our research questions. The results revealed positive main and negative interaction effects of conscientiousness, interest in German, and task interest on task effort and of conscientiousness and task interest on task achievement. No main effects of subject interest (German, chemistry, mathematics, or physics) on academic achievement were found. We found compensatory effects at the task level, as postulated by the CONIC model, provided a situational interest had been triggered or an individual interest activated, especially for effort. These findings may help to explain effects at a more aggregated level over time.

In this paper, we present the DARIUS (Digital Argumentation Instruction for Science) corpus for argumentationquality on 4589 essays written by 1839 German secondary school students. The corpus is annotated according toa fine-grained annotation scheme, ranging from a broader perspective like content zones, to more granular featureslike argumentation coverage/reach and argumentative discourse units like claims and warrants. The features haveinter-annotator agreements up to 0.83 Krippendorff’s α. The corpus and dataset are publicly available for furtherresearch in argument mining.