E-learning has shifted the traditional learning paradigms in higher education, offering more flexible, ubiquitous, and personalized learning experiences. The previous years COVID-19 pandemic required a re-calibration of education to accommodate virtual learning environments from the traditional classroom-based education. Widespread learning platforms and digital devices have accelerated the adoption of e-learning , and now, it plays a central role in formal and informal education.@en

Different individual features of the learner data often work as essential indicators of learning and intervention needs. This work exploits the personas in the design thinking process as the theoretical basis to analyze and cluster learners’ learning behavior patterns as groups. To adapt to the learning practice, we develop data-driven personas by clustering learners’ features based on factual learning outcomes (i.e., knowledge gain, perceived learning experience, perceived social presence) based on unsupervised learning, a more accessible and objective intervention design strategy for e-reading practices. Using the Chi-square test, we quantitatively evaluate different clusters driven by various unsupervised learning methods on the multimodal SKEP dataset. Furthermore, for a more practical real-life application, we achieved automatic persona prediction based on the attention regulation behaviors of learners. The subject-independent evaluation results indicate the best classification accuracy of 70% for the four-level classification task, differentiating three personas of learners with needs and another without feedback needs. It also shows that time-based sampling on both independent and cumulative learner behaviors works as robust predictors of learner personas, achieving a stable accuracy range of 65%-70% throughout the e-reading with the SVM classifier. Our work inspires the design of a real-time feedback loop for e-learning based on conversational agents.@en

Reading on digital devices has become more commonplace, while it often poses challenges to learners' attention. In this study, we hypothesized that allowing learners to reflect on their reading phases with an empathic social robot companion might enhance learners' attention in e-reading. To verify our assumption, we collected a novel dataset (SKEP) in an e-reading setting with social robot support. It contains 25 multimodal features from various sensors and logged data that are direct and indirect cues of attention. Based on the SKEP dataset, we comprehensively compared the difference between HRI-based (treatment) and GUI-based (control) feedback and obtained insights for intervention design. Based on the human annotation of the nearly 40 hours of video data streams from 60 subjects, we developed a machine learning model to capture attention-regulation behaviors in e-reading. We exploited a two-stage framework to recognize learners' observable self-regulatory behaviors and conducted attention analysis. The proposed system showed a promising performance with high prediction results of e-reading with HRI, such as 72.97% accuracy in recognizing attention regulation behaviors, 74.29% accuracy in predicting knowledge gain, 75.00% for perceived interaction experience, and 75.00% for perceived social presence. We believe our work can inspire the future design of HRI-based e-reading and its analysis.

@en

Technology-enhanced learning systems, specifically multimodal learning technologies, use sensors to collect data from multiple modalities to provide personalized learning support beyond traditional learning settings. However, many studies surrounding such multimodal learning systems mostly focus on technical aspects concerning data collection and exploitation and therefore overlook theoretical and instructional design aspects such as feedback design in multimodal settings. This paper explores multimodal learning systems as a critical part of technology-enhanced learning used for capturing and analyzing the learning process to exploit the collected multimodal data to generate feedback in multimodal settings. By investigating various studies, we aim to reveal the roles of multimodality in technology-enhanced learning across various learning domains. Our scoping review outlines the conceptual landscape of multimodal learning systems, identifies potential gaps, and provides new perspectives on adaptive multimodal system design: intertwining learning data for meaningful insights into learning, designing effective feedback, and implementing them in diverse learning domains.

@en

This study is built upon a behavior-based framework for real-time attention evaluation of higher education learners in e-reading. Significant challenges in AI model developments for learning analytics have been 1) defining valid indicators and 2) connecting the analytics results to interventions, balancing the generalization and personalization needs. To address this, we utilized a public multimodal WEDAR dataset and trained a neural network model based on real-time features of learners, aiming at predicting learners’ moment-to-moment distractions. Real-time features for model training include 30 learners’ attention regulation behaviors annotated every second, reaction times to blur stimuli, and page numbers indicating various reading phases. Our preliminary model based on a neural network has achieved 66.26% accuracy in predicting self-reported distractions. Based on the model, we suggest a framework of a Behavior-based Feedback Loop for Attentive e-reading (BFLAe). It has text blur as feedback, a mechanism responsive to learners’ distractions that also works as data for next-round feedback. The general feedback implementation rules are established on a statistical analysis conducted on all learners. In addition, we propose a strategy for personalizing feedback using a quartile analysis of individual data, promoting learner-specific feedback. Our framework addresses the high demand for an automated e-learning assistant with non-intrusive data collection based on real-world settings and intuitive feedback provision. The feedback system aims to help learners with longer attention spans and less frequent distractions, leading to more engaging e-reading. @en

Human attention is critical yet challenging cognitive process to measure due to its diverse definitions and non-standardized evaluation. In this work, we focus on the attention self-regulation of learners, which commonly occurs as an effort to regain focus, contrary to attention loss. We focus on easy-to-observe behavioral signs in the real-world setting to grasp learners' attention in e-reading. We collected a novel dataset of 30 learners, which provides clues of learners' attentional states through various metrics, such as learner behaviors, distraction self-reports, and questionnaires for knowledge gain. To achieve automatic attention regulator behavior recognition, we annotated 931,440 frames into six behavior categories every second in the short clip form, using attention self-regulation from the literature study as our labels. The preliminary Pearson correlation coefficient analysis indicates certain correlations between distraction self-reports and unimodal attention regulator behaviors. Baseline model training has been conducted to recognize the attention regulator behaviors by implementing classical neural networks to our WEDAR dataset, with the highest prediction result of 75.18% and 68.15% in subject-dependent and subject-independent settings, respectively. Furthermore, we present the baseline of using attention regulator behaviors to recognize the attentional states, showing a promising performance of 89.41% (leave-five-subject-out). Our work inspires the detection & feedback loop design for attentive e-reading, connecting multimodal interaction, learning analytics, and affective computing.

@en

Using Artificial Intelligence (AI) and machine learning technologies to automatically mine latent patterns from educational data holds great potential to inform teaching and learning practices. However, the current AI technology mostly works as "black box"-only the inputs and the corresponding outputs are available, which largely impedes researchers from gaining access to explainable feedback. This interdisciplinary work presents an explainable AI prototype with visualized explanations as feedback for computer-supported collaborative learning (CSCL). This research study seeks to provide interpretable insights with machine learning technologies for multimodal learning analytics (MMLA) by introducing two different explanatory machine learning-based models (neural network and Bayesian network) in different manners (end-to-end learning and probabilistic analysis) and for the same goal-provide explainable and actionable feedback. The prototype is applied to the real-world collaborative learning scenario with data-driven learning based on sensor-data from multiple modalities which can assess collaborative learning processes and render explanatory real-time feedback.@en

To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D neural network-based two-stream (Rank Pooling RGB and Optical Flow) framework for the task. The method is validated on the action recognition track of the ECCV 2020 VIPriors challenges and got the 2nd place (88.31%). It is proved that our method can achieve a promising result even without a pre-trained model on large scale datasets. The code will be released soon. @en