Understanding a student's problem-solving strategy can have a significant impact on effective math learning using Intelligent Tutoring Systems (ITSs) and Adaptive Instructional Systems (AISs). For instance, the ITS/AIS can better personalize itself to correct specific misconceptions that are indicated by incorrect strategies, specific problems can be designed to improve strategies and frustration can be minimized by adapting to a student's natural way of thinking rather than trying to fit a standard strategy for all. While it may be possible for human experts to identify strategies manually in classroom settings with sufficient student interaction, it is not possible to scale this up to big data. Therefore, we leverage advances in Machine Learning and AI methods to perform scalable strategy prediction that is also fair to students at all skill levels. Specifically, we develop an embedding called MVec where we learn a representation based on the mastery of students. We then cluster these embeddings with a non-parametric clustering method where each cluster contains instances that have approximately symmetrical strategies. The strategy prediction model is trained on instances sampled from these clusters ensuring that we train the model over diverse strategies. Using real world large-scale student interaction datasets from MATHia, we show that our approach can scale up to achieve high accuracy by training on a small sample of a large dataset and also has predictive equality, i.e., it can predict strategies equally well for learners at diverse skill levels.
more »
« less
AdapTutAR: An Adaptive Tutoring System for Machine Tasks in Augmented Reality
Modern manufacturing processes are in a state of flux, as they adapt to increasing demand for flexible and self-configuring production. This poses challenges for training workers to rapidly master new machine operations and processes, i.e. machine tasks. Conventional in-person training is effective but requires time and effort of experts for each worker trained and not scalable. Recorded tutorials, such as video-based or augmented reality (AR), permit more efficient scaling. However, unlike in-person tutoring, existing recorded tutorials lack the ability to adapt to workers’ diverse experiences and learning behaviors. We present AdapTutAR, an adaptive task tutoring system that enables experts to record machine task tutorials via embodied demonstration and train learners with different AR tutoring contents adapting to each user’s characteristics. The adaptation is achieved by continually monitoring learners’ tutorial-following status and adjusting the tutoring content on-the-fly and in-situ. The results of our user study evaluation have demonstrated that our adaptive system is more effective and preferable than the non-adaptive one.
more »
« less
- Award ID(s):
- 1839971
- NSF-PAR ID:
- 10297581
- Date Published:
- Journal Name:
- CHI Conference on Human Factors in Computing Systems (CHI '21)
- Page Range / eLocation ID:
- 1 to 15
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Solar flare prediction is a central problem in space weather forecasting and has captivated the attention of a wide spectrum of researchers due to recent advances in both remote sensing as well as machine learning and deep learning approaches. The experimental findings based on both machine and deep learning models reveal significant performance improvements for task specific datasets. Along with building models, the practice of deploying such models to production environments under operational settings is a more complex and often time-consuming process which is often not addressed directly in research settings. We present a set of new heuristic approaches to train and deploy an operational solar flare prediction system for ≥M1.0-class flares with two prediction modes: full-disk and active region-based. In full-disk mode, predictions are performed on full-disk line-of-sight magnetograms using deep learning models whereas in active region-based models, predictions are issued for each active region individually using multivariate time series data instances. The outputs from individual active region forecasts and full-disk predictors are combined to a final full-disk prediction result with a meta-model. We utilized an equal weighted average ensemble of two base learners’ flare probabilities as our baseline meta learner and improved the capabilities of our two base learners by training a logistic regression model. The major findings of this study are: 1) We successfully coupled two heterogeneous flare prediction models trained with different datasets and model architecture to predict a full-disk flare probability for next 24 h, 2) Our proposed ensembling model, i.e., logistic regression, improves on the predictive performance of two base learners and the baseline meta learner measured in terms of two widely used metrics True Skill Statistic (TSS) and Heidke Skill Score (HSS), and 3) Our result analysis suggests that the logistic regression-based ensemble (Meta-FP) improves on the full-disk model (base learner) by ∼9% in terms TSS and ∼10% in terms of HSS. Similarly, it improves on the AR-based model (base learner) by ∼17% and ∼20% in terms of TSS and HSS respectively. Finally, when compared to the baseline meta model, it improves on TSS by ∼10% and HSS by ∼15%.more » « less
-
Recent advances in Augmented Reality (AR) devices and their maturity as a technology offers new modalities for interaction between learners and their learning environments. Such capabilities are particularly important for learning that involves hands-on activities where there is a compelling need to: (a) make connections between knowledge-elements that have been taught at different times, (b) apply principles and theoretical knowledge in a concrete experimental setting, (c) understand the limitations of what can be studied via models and via experiments, (d) cope with increasing shortages in teaching-support staff and instructional material at the intersection of disciplines, and (e) improve student engagement in their learning. AR devices that are integrated into training and education systems can be effectively used to deliver just-in-time informatics to augment physical workspaces and learning environments with virtual artifacts. We present a system that demonstrates a solution to a critical registration problem and enables a multi-disciplinary team to develop the pedagogical content without the need for extensive coding. The most popular approach for developing AR applications is to develop a game using a standard game engine such as UNITY or UNREAL. These engines offer a powerful environment for developing a large variety of games and an exhaustive library of digital assets. In contrast, the framework we offer supports a limited range of human environment interactions that are suitable and effective for training and education. Our system offers four important capabilities – annotation, navigation, guidance, and operator safety. These capabilities are presented and described in detail. The above framework motivates a change of focus – from game development to AR content development. While game development is an intensive activity that involves extensive programming, AR content development is a multi-disciplinary activity that requires contributions from a large team of graphics designers, content creators, domain experts, pedagogy experts, and learning evaluators. We have demonstrated that such a multi-disciplinary team of experts working with our framework can use popular content creation tools to design and develop the virtual artifacts required for the AR system. These artifacts can be archived in a standard relational database and hosted on robust cloud-based backend systems for scale up. The AR content creators can own their content and Non-fungible Tokens to sequence the presentations either to improve pedagogical novelty or to personalize the learning.more » « less
-
Recent advances in Augmented Reality (AR) devices and their maturity as a technology offers new modalities for interaction between learners and their learning environments. Such capabilities are particularly important for learning that involves hands-on activities where there is a compelling need to: (a) make connections between knowledge-elements that have been taught at different times, (b) apply principles and theoretical knowledge in a concrete experimental setting, (c) understand the limitations of what can be studied via models and via experiments, (d) cope with increasing shortages in teaching-support staff and instructional material at the intersection of disciplines, and (e) improve student engagement in their learning. AR devices that are integrated into training and education systems can be effectively used to deliver just-in-time informatics to augment physical workspaces and learning environments with virtual artifacts. We present a system that demonstrates a solution to a critical registration problem and enables a multi-disciplinary team to develop the pedagogical content without the need for extensive coding. The most popular approach for developing AR applications is to develop a game using a standard game engine such as UNITY or UNREAL. These engines offer a powerful environment for developing a large variety of games and an exhaustive library of digital assets. In contrast, the framework we offer supports a limited range of human environment interactions that are suitable and effective for training and education. Our system offers four important capabilities – annotation, navigation, guidance, and operator safety. These capabilities are presented and described in detail. The above framework motivates a change of focus – from game development to AR content development. While game development is an intensive activity that involves extensive programming, AR content development is a multi-disciplinary activity that requires contributions from a large team of graphics designers, content creators, domain experts, pedagogy experts, and learning evaluators. We have demonstrated that such a multi-disciplinary team of experts working with our framework can use popular content creation tools to design and develop the virtual artifacts required for the AR system. These artifacts can be archived in a standard relational database and hosted on robust cloud-based backend systems for scale up. The AR content creators can own their content and Non-fungible Tokens to sequence the presentations either to improve pedagogical novelty or to personalize the learning.more » « less
-
more » « less
Abstract Intelligent tutoring systems (ITSs) incorporate pedagogical agents (PAs) to scaffold learners' self‐regulated learning (SRL) via prompts and feedback to promote learners' monitoring and regulation of their cognitive, affective, metacognitive and motivational processes to achieve their (sub)goals. This study examines PAs' effectiveness in scaffolding and teaching SRL during learning with MetaTutor, an ITS on the human circulatory system. Undergraduates (
N = 118) were randomly assigned to a condition:Control Condition (i.e. learners could only self‐initiate SRL strategies) andPrompt and Feedback Condition (i.e. PAs prompted learners to engage in SRL). Learners' log‐file data captured when strategies were used, the initiator of the strategy (i.e. learner and PA), and the relevance of instructional content pages in relation to learner subgoals. While results showed that PAs were effective scaffolders of SRL in which they prompted learners to engage in SRL strategies more when content was relevant towards their subgoals and as time on page and task increased, there were mixed findings about the effectiveness of PAs as teachers of SRL. Findings show how production rules guiding PA prompts can improve their scaffolding and teaching of SRL across the learning task – through contextualizing SRL strategies to the instructional content and in relation to the relevance of the content to learners' subgoals.Practitioner notes What is already known about this topic Most learners struggle to efficiently and effectively use self‐regulated learning (SRL) strategies to attain goals and subgoals.
There is a need for SRL to be scaffolded for learners to manage multiple goals and subgoals while learning about complex STEM topics.
Intelligent tutoring systems (ITSs) typically incorporate pedagogical agents (PAs) to prompt learners to engage in SRL strategy and provide feedback.
There are mixed findings on the effectiveness of PAs in scaffolding learners' SRL.
What this paper adds We consider PAs not only scaffolders but also teachers of SRL.
Results showed that while PAs encouraged the use of SRL strategies when the content was relevant to subgoals, they did not discourage the use of SRL strategies when the content was not relevant.
Results for this study were mixed in their support of PAs as teachers of SRL.
Learners increasingly depended on PAs to prompt SRL strategies as time on task progressed.
Implications for practice and/or policy PAs are effective scaffolders of SRL with more research needed to understand their role as teachers of SRL.
PA scaffolding is more essential as time on task progresses.
When deploying specific cognitive and metacognitive SRL strategies, the relevance of the content to learners' subgoals should be taken into account.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3411764.3445283
