Search

Modeling reading comprehension processes is a critical task for Learning Analytics, as accurate models of the reading process can be used to match students to texts, identify appropriate interventions, and predict learning outcomes. This paper introduces an improved version of the Automated Model of Comprehension, namely version 4.0. AMoC has its roots in two theoretical models of the comprehension process (i.e., the Construction-Integration model and the Landscape model), and the new version leverages state-of-the-art Large Language models, more specifically ChatGPT, to have a better contextualization of the text and a simplified construction of the underlying graph model. Besides showcasing the usage of the model, the study introduces three in-depth psychological validations that argue for the model's adequacy in modeling reading comprehension. In these studies, we demonstrated that AMoC is in line with the theoretical background proposed by the Construction-Integration and Landscape models, and it is better at replicating results from previous human psychological experiments than its predecessor. Thus, AMoC v4.0 can be further used as an educational tool to, for example, help teachers design better learning materials personalized for student profiles. Additionally, we release the code from AMoC v4.0 as open source in a Google Collab Notebook and a GitHub repository. • Introduce the Automated Model of Comprehension version 4.0 that integrates state-of-the-art Large Language models - ChatGPT. • Perform 3 in-depth psychological validation studies to support the model's adequacy in modeling reading comprehension. • AMoC v4.0 aligns with theoretical frameworks, namely Construction-Integration and Landscape models. • The model outperforms its predecessor and replicates results from human psychological experiments. • AMoC v4.0 can serve as an educational tool for designing personalized learning materials. [ABSTRACT FROM AUTHOR]

Web personalization has been widely adopted in the mobile shopping context to improve shopping experience and consumer loyalty. Timing is a crucial issue of the implementation of web personalization, a topic not yet adequately investigated in the extant literature. Web personalization could classify into two forms, namely Before-search Web Personalization (BSWP) and After-search Web Personalization (ASWP), in the mobile shopping context. Besides, motivations are the critical factors in mobile shopping, and seldom research has studied the effects of motivation on consumer's use of web personalization in the mobile shopping context. To advance understanding of the timing issue of web personalization, this paper employs the Uses and Gratifications method to investigate how mobile shopping motivations influence consumers' use of BSWP and ASWP, respectively. Furthermore, this paper also investigates the role of an important personal disposition (i.e. need for cognition). Empirical results indicate that shopping motivations could have significant effects on web personalization use; furthermore, BSWP use and ASWP use are predicted by different shopping motivations. Besides, need for cognition is found to positively moderate some effects of mobile shopping motivations on web personalization use. Theoretical and practical implications are also discussed. [ABSTRACT FROM AUTHOR]

Organizations are increasingly flooded with large amounts of data on which they base their business decisions. It is thus crucial to visualize relevant data efficiently so that employees are able to extract relevant information most accurately and quickly. However, at present, information visualization research lacks a coherent and evidence based theoretical framework providing clear guidelines on how to design efficient visualizations. When it comes to the use of redundant elements in charts like commonly used data labels, cognitive fit theory and cognitive load theory make different predictions. Whereas the latter assumes that redundant labels generally reduce visualizations’ efficiency due to increased cognitive load, cognitive fit theory predicts increased efficiency for some task types that shall be solved by means of the visualization. In the online experiment presented in this paper, we investigated the effect of data labels in line and bar charts on users’ accuracy and speed in solving chart-related business tasks dependent on different task types. Our results reveal that users perceive charts with redundant labels as significantly more efficient and answer related questions significantly more accurate and faster, which we explain by the help of cognitive fit theory. We provide valuable insights into cognitive processing of charts and encourage graph designers to consider redundant elements as a possible means to increase efficiency under particular circumstances. [ABSTRACT FROM AUTHOR]

Decision justification provides assurance and reduces negative post-decision emotions, while simultaneously expends decision costs (i.e., cognitive effort). The current paper investigated the function of justification and cognitive effort related to regret, specifically in the online shopping context in two studies. In Study 1, 112 participants reviewed vignettes in a 2 × 2 within-subjects design involving cognitive effort (high versus low) and justification of action (easy versus difficulty), and reported the regret level when their purchase decision yielded subpar consequences. As expected, high cognitive effort and easy justification reduced regret. However, the effect of justification on regret was moderated by cognitive effort. In Study 2, 178 participants were randomly assigned to conditions in a 2 × 2 between-subjects design involving cognitive effort (high versus low) and decision justification (waste versus control). Participants followed a cover story and shopped for a laptop online; then they rated the regret level had they made an unplanned purchase. Results confirmed the hypothesis; regret was greater when justification was wasted. However, wasted justification only worsened regret when more cognitive effort was exerted. The current studies shed light on understanding an intricate dynamic between information processing and justification in relation to regret when shopping online. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we explore how visual representations of information in 3D virtual environments (3DVEs) supports both individual and shared understanding, and consequently contribute to group decision making in tasks with a strong visual component. We integrate insights from cognitive fit theory and cognitive load theory in order to formulate hypotheses about how 3DVEs can contribute to individual understanding, shared understanding, and group decision making. We discuss the results of an experiment in which 192 participants, in 3-person teams, were asked to select an apartment. As proposed by cognitive fit theory, our results indicate that 3DVEs are indeed more effective in supporting individual understanding than 2D information presentations. Next, in line with cognitive load theory, the static presentation of 3D information turns out to be more effective in supporting shared understanding and group decision making than an immersive 3DVE. Our results suggest that although the 3DVE capabilities of realism, immersion and interactivity contribute to individual understanding, these capabilities combined with the interaction and negotiation processes required for reaching a shared understanding (and group decision), increases cognitive load and makes group processes inefficient. The implications of this paper for research and practice are discussed. [Copyright &y& Elsevier]

Abstract: Intelligent tutoring systems often make use of students’ answers to adapt instruction or feedback on a task. In this paper, we explore the alternative possibility of adapting a system based on the perceived affective and cognitive state of a student. A system can potentially better adapt to the needs of each individual student by using non-verbal behavior. We used a new experimental paradigm inspired by ‘brain training’ software to collect primary school children’s answers to easy and difficult arithmetic problems and made audiovisual recordings of their answers. Adult observers rated these films on perceived difficulty level. Results showed that adults were able to correctly interpret children’s perceived level of difficulty, especially if they saw their face (compared to hearing their voice). They paid attention to features such as ‘looking away’, and ‘frowning’. Then we checked whether we could also automatically predict if the posed problem was either easy or difficult based on the first second of their response. This ‘thin-slice analysis’ could correctly predict the difficulty level in 71% of all cases. When trained on sufficiently many recordings, Adaptive Tutoring Systems should be able to detect children’s state and adapt the difficulty level of their learning materials accordingly. [Copyright &y& Elsevier]