Perceived Task-Difficulty Recognition from Log-file Information for the Use in Adaptive Intelligent Tutoring Systems

Abstract

Recognising students' emotion, affect or cognition is a relatively young field and still a challenging task in the area of intelligent tutoring systems. There are several ways to use the output of these recognition tasks within the system. The approach most often mentioned in the literature is using it for giving feedback to the students. The features used for that approach can be high-level features like linguistics features which are words related to emotions or affects, taken e.g. from written or spoken inputs, or low-level features like log-file features which are created from information contained in the log-files. In this work we aim at supporting task sequencing by perceived task-difficulty recognition on low-level features easily extracted from the log-file. We analyse these features by statistical tests showing that there are statistically significant feature combinations and hence the presented features are able to describe students' perceived task-difficulty in intelligent tutoring systems. Furthermore, we apply different classification methods to the log-file features for perceived task-difficulty recognition and present a kind of higher ensemble method for improving the classification performance on the features extracted from a real data set. The presented approach outperforms classical ensemble methods and is able to improve the classification performance substantially, enabling a perceived task-difficulty recognition satisfactory enough for employing its output for components of a real system like task independent support or task sequencing.

Affective learning: improving engagement and enhancing learning with affect-aware feedback

“…Schuller et al, 2005) and a naive Bayes classifier was used to classify the student's a↵ective state ). -What we call the perceived task di culty classifier (PTDC ), extracts prosodic features (such as 'um's and pauses) from the student's speech and uses speech and pause histograms to infer whether the student is under-, appropriately or over-challenged (Janning et al, 2014(Janning et al, , 2016. The prosodic features were extracted from the voice recordings of the Wizard-of-Oz studies, based on two independent coders who classified a student's level of challenge by taking into account the student's speech and interaction with the learning environment.…”

Cognitive Load in Solving Mathematics Problems: Validating the Role of Motivation and the Interaction Among Prior Knowledge, Worked Examples, and Task Difficulty

“…That is, the task difficulty was mitigated due to an adaption of the content to the learner's domain prior knowledge. So far, the research on task difficulty in light of domain prior knowledge and instructional strategy has been focused on (a) the interaction between task difficulty and instructional strategy (Janning, Schatten, & Schmidt-Thieme, 2016) and (b) the supplementary role of domain prior knowledge (Orvis et al, 2008). There is no study, to the best of our knowledge, that exploits the interaction between task difficulty and instructional strategy based on expertise reversal effect principle.…”

Exploring Students’ Affective States During Learning with External Representations

“…This is used to detect and analyse student's speech in near real time (c.f. [6]). The analysis of the speech and students' interaction with the exploratory learning environment are used to detect their affective states.…”