2021, Volume 24, Issue 1

Special Issue on "Precision Education - A New Challenge for AI in Education"

Guest Editor(s): Stephen J. H. Yang

Download Table of Content in PDF

Download Complete Issue in PDF

Full Length Articles

Yun Wen

National Institute of Education (NIE), Nanyang Technological University, Singapore // yun.wen@nie.edu.sg

Yanjie Song

Education University of Hong Kong // ysong@eduhk.hk


Learning analytics (LA) has been increasingly using in teaching and learning. However, in the field of applied linguistics, the use of LA has only begun to touch the surface. There is a need for understanding how LA and learning design (LD) influence each other and provide useful information to language teachers in the context of specific courses or learning environments. In this study, a retrospective analysis was conducted to identify the factors influencing LA for collaborative language learning in classrooms, from a holistic perspective by integrating LA, LD, and teacher inquiry. The findings suggested that (1) LA focused on interactions can inform pedagogical refinement effectively when LD in language learning is premised on social constructivist theories; (2) LA supported teacher inquiry and LD on condition that the teacher holds innovation-oriented beliefs and the participatory culture between teachers and researchers. The study provided insights into the use of LA in collaborative language learning classrooms that focus on collecting and evaluating learners’ interaction process beyond gleaning linguistic or behavioral facts. Professional development implications and future research are also addressed.


Learning analytics, Learning design, Teacher inquiry, Second language learning, Collaborative language learning

Mehmet Kokoç

School of Applied Sciences, Trabzon University, Turkey // kokoc@trabzon.edu.tr

Mehmet Kara

Vocational School of Design, Amasya University, Turkey // mehmet.kara@amasya.edu.tr


The purposes of the two studies reported in this research are to adapt and validate the instrument of the Evaluation Framework for Learning Analytics (EFLA) for learners into the Turkish context, and to examine how metacognitive and behavioral factors predict learner performance. Study 1 was conducted with 83 online learners enrolled in a 16-week course delivered through the Moodle learning management system. The findings from the confirmatory factor analysis indicated that a three-factor model of the EFLA for learners provided the best model fit for the collected data. The model is consistent with the factorial structure of the original instrument developed based on the data from the European learners. Study 2 aimed to reveal how the metacognitive and behavioral factors pertaining to the learning analytics dashboard predict learners’ academic performance. A total of 63 online learners enrolled in a 14-week online computing course participated in this study. The results from the logistic regression analysis indicated that online learners more frequently interacted with the learning analytics dashboard demonstrated greater academic performance. Furthermore, the dimensions of the EFLA, together with the interaction with the dashboard, significantly predicted learners’ academic performance. This multiple-study investigation contributes to the generalizability of the EFLA for learners and highlights the importance of metacognitive and behavioral factors for the impact of learning analytics dashboards on learner performance.


Learning analytics, Learning analytics dashboards, Evaluation, Validation, Learning performance

Sarah D. Matthews

University of Central Florida, College of Engineering and Computer Science, Orlando, FL, USA // Sarah.Matthews@knights.ucf.edu

Michael D. Proctor

University of Central Florida, College of Engineering and Computer Science, Orlando, FL, USA // Michael.Proctor@ucf.edu


The COVID-19 pandemic hit the United States in 2020 resulting in a public health caseload surge precipitating deployment of military and federal medical units, states issuing emergency orders to engage retired medical professionals, and novice or inadequately trained healthcare workers thrust into service to meet the pressing need. The novelty and scope of the pandemic exposed a gap in the competency and the surge capacity of the public health workforce to address the societal needs during the pandemic. This research investigated the capability of an agent-based, online personalized (AOP) intelligent tutoring system (ITS) that adaptively uses aptitude treatment interaction (ATI) to deliver public health workforce training in a prescribed health regime and assure their competency. This research also considers the ability of such an AOP ITS to support rapidly surging capacity of the public workforce to scale to meet healthcare demands while remaining accessible and flexible enough to adapt to changing healthcare guidance. Findings indicate such a system increases participant performance while providing a high level of acceptance, ease of use by users, and competency assurance. However, discussion of our findings indicates limited potential for an AOP ITS using the current ATI paradigm to make a major contribution to adding public health workforce surge capacity unless workforce members are directed to utilize it and technology barriers in the current public health IT infrastructure are overcome.


Agent, Intelligent tutoring system, Public health, Surge capacity, Competencies

Biyun Huang

Centre for Learning Sciences and Technologies, The Chinese University of Hong Kong, Hong Kong SAR, China // lucyhuang99@cuhk.edu.hk

Khe Foon Hew

Faculty of Education, The University of Hong Kong, Hong Kong SAR, China // kfhew@hku.hk


A design-based study was conducted in iterative cycles to test the effectiveness of the updated goal-access-feedback-challenge-collaboration (updated-GAFCC) gamification design model. The test-bed was a 10-week undergraduate introductory information management course. Students from three consecutive school years participated in the study, with the control group studying the conventional course without gamification (first year), treatment group_1 studying a gamified course following the original GAFCC model (second year), and treatment group_2 studying an optimized gamified course following the updated-GAFCC model (third year). The results of the design-based study indicated that (i) the updated-GAFCC model and the GAFCC model were effective in enhancing students’ learning achievements and task completion; (ii) the updated-GAFCC model was more successful in generating higher quality thinking artifacts than the GAFCC model; (iii) there were fewer lower-quality submissions in the updated-GAFCC condition than in the GAFCC condition; and (iv) 89% of the interviewed students in the updated-GAFCC condition were satisfied with the overall learning design, and felt that the gamified learning activities facilitated their learning. Overall, the findings contribute to our understanding of how pedagogical strategies can be incorporated into the theory-based design model to optimize learning experiences and academic outcomes.


Gamification, Design model, Design-based research, Learning performance, Long-term

Organizing and Hosting Virtual PPTELL 2020 During the COVID-19 Pandemic

Yu-Ju Lan, Kao Chia-Ling Gupta, Tai-Yi Huang, Shobhana Chelliah and J. Michael Spector

Yu-Ju Lan

National Taiwan Normal University, Taiwan // yujulan@gmail.com

Kao Chia-Ling Gupta

University of Hong Kong, China // kclgupta@gmail.com

Tai-Yi Huang

University of North Texas, USA // Tai-yi.huang@unt.edu

Shobhana Chelliah

University of North Texas, USA // Shobhana.Chelliah@unt.edu

J. Michael Spector

University of North Texas, USA // Mike.Spector@unt.edu


This paper aims at answering the “how” questions about organizing and hosting an online conference during the COVID-19 pandemic. The 3rd International Pan-Pacific Technology-Enhanced Language Learning (PPTELL) Conference and Critical Thinking Meeting (hereafter PPTELL 2020) hosted from June 29 to July 1, 2020, on Zoom is the example conference used in this paper to illustrate the challenges and approaches adopted before, during and after the conference. The mentioned conference was supposed to take place physically at the University of North Texas during the same period but was transformed into an online virtual conference due to the outbreak of COVID-19 in early 2020. It was an urgent decision, along with many unknown situations, such as the attendees’ different time zones and “Zoombombing.” A three-staged and target-action process guided the preparation and organization of the online conference, i.e., pre-, during, and post-conference. According to the live meeting results and the post-conference survey, PPTELL 2020 has earned a reputation from its quality and the satisfaction of the participants and attendees. Therefore, the experience shared in the current paper seems to be a good reference for the organizers and hosts of international conferences.


Online conference, COVID-19, Zoombombing, PPTELL 2020 and Critical Thinking Meeting

Using Data Analytics to Investigate Attendees’ Behaviors and Psychological States in a Virtual Academic Conference

Jiun-Yu Wu, Chen-Hsuan Liao, Mei-Wen Nian and Tzuying Cheng

Margus Pedaste

Institute of Education, University of Tartu, Estonia // margus.pedaste@ut.ee

Meriliis Kasemets

Institute of Education, University of Tartu, Estonia // meriliis.kasemets@ut.ee

ABSTRACT: Travel restrictions regarding COVID-19 have created new challenges for organizing international scientific conferences. Most of the conferences have to be moved to a fully online format. In our study, we analyzed what challenges it created in organizing the International Conference on Advanced Learning Technologies and Technology-Enhanced Learning in July 2020 in Estonia at the University of Tartu. The conference had 131 attendees from all over the world – this resulted in significant challenges due to differences in time zones and difficulties in engaging and socializing people in an online event. In our study, we collected feedback on conference-organization related challenges from five local organizing team members with different roles in the team. Their interviews were analyzed using an abductive approach. The results showed that the challenges could be identified through eight main categories: value, management, timing, program, people, protection, scaffolds, and money. In each of them, several sub-categories were specified. It was concluded that there were both advantages and challenges in organizing an online conference compared to a regular one. For example, fewer challenges are related to travel, accommodation, food and drinks, but more attention needs to be paid to supporting the socialization of people, especially those living in different time zones. Another major challenge appeared to be uncertainty related to the conference budget. Significant advantages were that the carbon footprint of the conference was smaller, the conference was more accessible, and it was easier to solve all the technical issues of the participants.

Keywords: Online conference, COVID-19, ICALT, Zoom, Remo, Abductive analysis


Stephen J. H. Yang

National Central University, Taiwan // Stephen.Yang.Ac@gmail.com

ABSTRACT: As addressed by Stephen Yang in his ICCE 2019 keynote speech (Yang, 2019), precision education is a new challenge when applying artificial intelligence (AI), machine learning, and learning analytics to improve teaching quality and learning performance. The goal of precision education is to identify at-risk students as early as possible and provide timely intervention on the basis of teaching and learning experiences (Lu et al., 2018). Drawing from this main theme of precision education, this special issue advocates an in-depth dialogue between cold technology and warm humanity, in turn offering greater understanding of precision education. For this special issue, thirteen research papers that specialize in precision education, AI, machine learning, and learning analytics to engage in an in-depth research experiences concerning various applications, methods, pedagogical models, and environments were exchanged to achieve better understanding of the application of AI in education.

Keywords: Precision education, Artificial intelligence, Learning analytics, Human-centered AI

Special Issue Articles

Dirk Tempelaar

Maastricht University, School of Business and Economics, The Netherlands // d.tempelaar@maastrichtuniversity.nl

Bart Rienties

The Open University, Institute of Educational Technology, UK // bart.rienties@open.ac.uk

Quan Nguyen

School of Information, University of Michigan, Ann Arbor, MI, USA // quanngu@umich.edu

ABSTRACT: Precision education requires two equally important conditions: accurate predictions of academic performance based on early observations of the learning process and the availability of relevant educational intervention options. The field of learning analytics (LA) has made important contributions to the realisation of the first condition, especially in the context of blended learning and online learning. Prediction models that use data from institutional information systems and logs of learning management systems have gained a good reputation in predicting underperformance and dropout risk. However, less progress is made in resolving the second condition: applying LA generated feedback to design educational interventions. In our contribution, we make a plea for applying dispositional learning analytics (DLA) to make LA precise and actionable. DLA combines learning data, as in LA, with learners’ disposition data measured through self-report surveys. The advantage of DLA is twofold: first, it improves the accuracy of prediction, specifically early in the module, when limited LMS trace data are available. Second, the main benefit of DLA is in the design of effective interventions: interventions that focus on addressing individual learning dispositions that are less developed but important for being successful in the module. We provide an empirical analysis of DLA in an introductory mathematics module, demonstrating the important role that a broad range of learning dispositions can play in realising precision education.

Keywords: Blended learning, Dispositional learning analytics, Educational intervention, Flipped learning, Precision education

Hui-Chen Lin

Department of Neurology, Tri-Service General Hospital National Defense Medical Center, Taiwan // ceciliatsgh@gmail.com

Yun-Fang Tu

Department of Library and Information Science, Research and Development Center for Physical Education, Health, and Information Technology, Fu Jen Catholic University, Taiwan // sandy0692@gmail.com

Gwo-Jen Hwang

Graduate Institute of Digital Learning and Education, National Taiwan University of Science and Technology, Taiwan // gjhwang.academic@gmail.com

Hsin Huang

Department of Nursing, Tri-Service General Hospital National Defense Medical Center, Taiwan // jhshing1029@gmail.com

ABSTRACT: Precision medicine has become an essential issue in the medical community as the quality of medical care is being emphasized nowadays. The technological data analysis and predictions made by Artificial Intelligence (AI) technologies have assisted medical staff in designing personalized medicine for patients, making AI technologies an important path to precision medicine. During the implementation of the new emerging technology, medical staff’s learning intentions will have a great influence on its effectiveness. With reference to the Technology Acceptance Model, this study explored medical staff’s attitudes, intentions, and relevant influencing factors in relation to AI application learning. A total of 285 valid questionnaires were collected. Five major factors, perceived usefulness (PU), perceived ease of use (PEU), subjective norms (SN), attitude towards AI use (ATU), and behavioral intention (BI), were used for analyzing the AI learning of medical staff in a hospital. Based on the SEM analytical results and the research model, the four endogenous constructs of PU, PEU, SN, and ATU explained 37.4% of the changes in BI. In this model, SN and PEU were the determining factors of BI. The total effects of SN and PEU were 0.448 and 0.408 respectively, followed by PU, with a total effect of 0.244. As a result, the intentions of medical staff to learn to use AI applications to support precision medicine can be predicted by SN, PEU, PU, and ATU. Among them, subjective norms considering the influences of both supervisors and peers, such as encouragement, communication, and sharing, may assist precision education in supporting the learning attitudes and behavior regarding precision medicine. The research results can provide recommendations for examining medical staff’s intention to use AI applications.

Keywords: Artificial intelligence, Subjective norms, Precision medicine, Precision education, Technology Acceptance Model

Fuzheng Zhao

Kobe University, Japan // zhaofz635@gmail.com

Gwo-Jen Hwang

National Taiwan University of Science and Technology, Taiwan // gjhwang.academic@gmail.com

Chengjiu Yin

Kobe University, Japan // yin@lion.kobe-u.ac.jp

ABSTRACT: Educational data mining and learning analytics have become a very important topic in the field of education technology. Many frameworks have been proposed for learning analytics which make it possible to identify learning behavior patterns or strategies. However, it is difficult to understand the reason why behavior patterns occur and why certain strategies are used. In other words, all of the existing frameworks lack an important step, that is, result confirmation. In this paper, we propose a Result Confirmation-based Learning Behavior Analysis (ReCoLBA) framework, which adds a result confirmation step for exploring the hidden reasons underlying the learning patterns and strategies. Using this ReCoLBA framework, a case study was conducted which analyzed e-book reading data. In the case study, we found that the students had a tendency to delete markers after adding them. Through an investigation, we found that the students did this because they could not grasp the learning emphasis. To apply this finding, we proposed a learning strategy whereby the teacher highlights the learning emphasis before students read the learning materials. An experiment was conducted to examine the effectiveness of this strategy, and we found that it could indeed help students achieve better results, reduce repetitive behaviors and save time. The framework was therefore shown to be effective.

Keywords: Learning analytics, Learning behavior pattern, Learning Analysis framework, Result confirmation

Toward Precision Education: Educational Data Mining and Learning Analytics for Identifying Students’ Learning Patterns with Ebook Systems

Christopher C. Y. Yang, Irene Y. L. Chen and Hiroaki Ogata

From Human Grading to Machine Grading: Automatic Diagnosis of e-Book Text Marking Skills in Precision Education

Albert C. M. Yang, Irene Y. L. Chen, Brendan Flanagan and Hiroaki Ogata

An Analytical Approach for Detecting and Explaining the Learning Path Patterns of an Informal Learning Game

Xuanqi Feng and Masanori Yamada

Analytics 2.0 for Precision Education: An Integrative Theoretical Framework of the Human and Machine Symbiotic Learning

Jiun-Yu Wu, Christopher C. Y. Yang, Chen-Hsuan Liao and Mei-Wen Nian

Predicting Students’ Academic Performance by Their Online Learning Patterns in a Blended Course: To What Extent Is a Theory-driven Approach and a Data-driven Approach Consistent?

Feifei Han and Robert A. Ellis

Twenty Years of Personalized Language Learning: Topic Modeling and Knowledge Mapping

Xieling Chen, Di Zou, Haoran Xie and Gary Cheng

Unfolding Students’ Online Assignment Submission Behavioral Patterns using Temporal Learning Analytics

Mehmet Kokoç, Gökhan Akçapınar and Mohammad Nehal Hasnine

Determining Quality and Distribution of Ideas in Online Classroom Talk using Learning Analytics and Machine Learning

Alwyn Vwen Yen Lee

A Review of Using Machine Learning Approaches for Precision Education

Hui Luan and Chin-Chung Tsai

Using an Institutional Research Perspective to Predict Undergraduate Students’ Career Decisions in the Practice of Precision Education

Tzu-Chi Yang, Yih-Lan Liu and Li-Chun Wang

Starting from Volume 17 Issue 4, all published articles of the journal of Educational Technology & Society are available under Creative Commons CC-BY-ND-NC 3.0 license.