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]

Every day we trust other individuals as we engage in social interactions in which various desirable outcomes depend on others acting the way we hope, or they have indicated. Trust extends beyond specific individuals, however, as we might trust unknown others – individuals, institutions, corporations, and governments. Some also say that we trust various artifacts, such as machines. But what is the basis of trust, and can we really trust technology? Trust is intimately connected to the notion ethos from the study of rhetoric and human persuasion, which is often used to describe various characteristics of the speaker, the audience, the relationship between the speaker and the audience, and the wider context in which communication and interaction occurs. In this article I explore to what degree machines can be considered to have ethos, and consequently whether ethos is a useful concept for understanding persuasive and credibility-related situations in HMI and by extension key aspects of human-machine trust. This allows us to draw on a long lineage of research from, for example, rhetoric, communication studies, and cognitive and social psychology to better understand the usefulness – or not – of using the notion of trust to describe our relationship with machines. • Trust in machines partly parallels trust in humans, institutions, and artifacts. • Ethos, from rhetoric, relates to credibility and trust in human-machine interaction. • This paper explores if machines can have ethos, and how this relates to trust. • Machine ethos is about perceived credibility and not the machine's ethics. • Examining ethos enriches understanding of trust and design in HMI. [ABSTRACT FROM AUTHOR]