SIMPLIFY ITS: An intelligent tutoring system based on cognitive diagnosis models and spaced learning

Villanueva, Nora M.; Costas, A.; Hermida, David Fernández; Rodriguez, Agustín Cañas

doi:10.1109/educon.2018.8363440

Cited by 5 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Domain models (19; 45.2%) were those informed by specific attributes of a curriculum, or a learning activity (with green in Figure 7). These included indicators such as typical errors made in tasks, task difficulty, or mapping knowledge items to tasks (e.g., Villanueva et al, 2018, used a cognitive diagnosis for mapping). Instructional models (13; 30%), based on rules about how to guide learners' learning, such as hints, explanations, or repetitions (e.g., Holstein, McLaren, & Aleven, 2018 that uses metrics about hints and explanation messages used by students when doing maths tasks). Collaborative models (7; 16.7%), generated information usually guided by a collaboration script, such as in Amarasinghe et al (2020) that used a pyramid collaboration script. Social models (8; 19.1%), used indicators based on the interactions of students or with learning resources. For example, Diana et al (2017) made use of social networks based on students' interactions, while Ruiz‐Calleja et al (2016) based on artefact‐learner connections.…”

Section: Resultsmentioning

confidence: 99%

“…These included indicators such as typical errors made in tasks, task difficulty, or mapping knowledge items to tasks (e.g., Villanueva et al, 2018, used a cognitive diagnosis for mapping). As can be seen in Figure 8, it was not common that the generated information was based on more than three models.…”

Section: What Data and Models Have Been Used And How Has The Informat...mentioning

confidence: 99%

See 1 more Smart Citation

Towards a partnership of teachers and intelligent learning technology: A systematic literature review of model‐based learning analytics

Ley

Tammets

Pishtari

et al. 2023

Computer Assisted Learning

View full text Add to dashboard Cite

BackgroundWith increased use of artificial intelligence in the classroom, there is now a need to better understand the complementarity of intelligent learning technology and teachers to produce effective instruction.ObjectiveThe paper reviews the current research on intelligent learning technology designed to make models of student learning and instruction transparent to teachers, an area we call model‐based learning analytics. We intended to gain an insight into the coupling between the knowledge models that underpin the intelligent system and the knowledge used by teachers in their classroom decision making.MethodsUsing a systematic literature review methodology, we first identified 42 papers, mainly from the domain of intelligent tutoring systems and learning analytics dashboards that conformed to our selection criteria. We then qualitatively analysed the context in which the systems were applied, models they used and benefits reported for teachers and learners.Results and ConclusionsA majority of papers used either domain or learner models, suggesting that instructional decisions are mostly left to teachers. Compared to previous reviews, our set of papers appeared to have a stronger focus on providing teachers with theory‐driven insights and instructional decisions. This suggests that model‐based learning analytics can address some of the shortcomings of the field, like meaningfulness and actionability of learning analytics tools. However, impact in the classroom still needs further research, as in half of the cases the reported benefits were not backed with evidence. Future research should focus on the dynamic interaction between teachers and technology and how learning analytics has an impact on learning and decision making by teachers and students. We offer a taxonomy of knowledge models that can serve as a starting point for designing such interaction.

show abstract