Speech Title:
Investigations into Deep Knowledge Tracing: From Cold-Start to Real Life

Dr Ryan Baker

Associate Professor at the University of Pennsylvania, and Director of the Penn Center for Learning Analytics, US


 
Speech Abstract

In the last several years, there has been increasing interest in studying different variants of deep knowledge tracing (DKT). However, deep knowledge tracing has remained largely an algorithm studied rather than an algorithm used. Real-world adaptive learning systems generally still use algorithms developed over a decade ago, or even simpler heuristics. In this talk, I discuss our research group's investigations into key issues relevant to the use of deep knowledge tracing, complementary to other research efforts going on around the world and in particular in East Asia. I will talk about two tracks of research in my group. In the first track of research, we investigate the use of DKT to estimate latent knowledge in terms of interpretable skills that can be carried outside the adaptive learning system. We propose a simple extension, applicable to all DKT family algorithms, and evaluate the degree to which DKT family algorithms can predict latent knowledge demonstrated on tests outside the learning system. In the second track of research, we study the degree to which DKT family algorithms can solve cold-start problems, producing acceptable knowledge tracing estimates earlier in student work on a new skill. I conclude with a discussion of directions needed for DKT family algorithms to achieve their full potential and scale in real-world use.

Speaker Bio
Ryan Baker is Associate Professor at the University of Pennsylvania, and Director of the Penn Center for Learning Analytics. His lab conducts research on engagement and robust learning within online and blended learning, seeking to find actionable indicators that can be used today but which predict future student outcomes. Baker has developed models that can automatically detect student engagement in over a dozen online learning environments, and has led the development of an observational protocol and app for field observation of student engagement that has been used by over 150 researchers in 7 countries. Predictive analytics models he helped develop have been used to benefit over a million students, over a hundred thousand people have taken MOOCs he ran, and he has coordinated longitudinal studies that spanned over a decade. He was the founding president of the International Educational Data Mining Society, is currently serving as Editor of the journal Computer-Based Learning in Context, is Associate Editor of the Journal of Educational Data Mining, was the first technical director of the Pittsburgh Science of Learning Center DataShop, and currently serves as Co-Director of the MOOC Replication Framework (MORF). Baker has co-authored published papers with over 300 colleagues.

Speech Title(題目):
具親子共讀策略之擴增實境繪本

Professor Chang Kuo-En
張國恩教授

Professor, Graduate Institute of Information and Computer Education, Taiwan Normal University
臺灣師範大學資訊教育研究所教授


 
Speaker Abstract(摘要)

親子共讀是父母、幼兒教育者和其他照料者幫助兒童獲得語言與文字認知發展與學習行為技能的一種方式。 對話式閱讀 (Dialog Reading)是一種以證據為基礎的常用親子共讀策略,其中PEER(Prompt, Evaluate, Expand, Repeat)更能促進親子互動之學習行為。然而由於父母並未受過對話式閱讀策略之訓練,因此並未表現出親子共讀效果。另外因父母需兼顧工作,較沒有充裕的時間陪伴兒童進行閱讀。為了能夠改善父母不會運用PEER策略與沒有時間陪兒童做親子共讀等問題,故運用AR技術發展具PEER親子共讀策略的AR繪本。在此AR繪本上,能引導兒童利用行動載具進行PEER之共讀,也探討此AR繪本對兒童學習成效與行為分析的影響。

Speaker Bio
張國恩從台灣大學獲電機博士後,在臺師大任教超過三十年,擔任過電算中心主任、資訊教育研究所所長、圖書館館長、副校長等職,2010年接下校長一職,帶領臺師大全面發展。期間創辦「數位學習與內容學會」與「新媒體科技與教育協會」,並擔任首屆理事長,納入「數位學習科技期刊」與「TWELF 學術會議」,也完成「新聞媒體識讀素養指標與量表」與發展相關課程,培養全民具備 「識讀能力」。此外,他也曾擔任國科會科教處資訊教育學門召集人,創設SIG研究群與薪火相傳會議,持續推動台灣數位學習研究。台師大校長任期屆滿後,現為台師大資訊教育研究所與運動科學系合聘講座教授。

張國恩從事數位學習相關研究,從早期的概念圖輔助教學、電腦模擬輔助學習、與行動學習外,也建立用於企業的數位學習品質認證指標,並於2011年建立了「華語文與科技研究中心」,整合團隊,從事華語文資訊科技在寫作、閱讀、語音辨識等研究。目前的研究工作集中在擴增實境(Augmented Reality)的教育應用,探討如何將擴增實境技術應用於輔助紙本書籍的閱讀上,結合精熟學習策略,在實體書籍上擴增輔助學習資訊,建構新的書本型態,稱為麻布書 (MAR Book,Mastery learning-based AR Book),同時也將AR技術應用在親子共讀與角色扮演的桌遊學習上。在後疫情時代,有鑑於遠距教學的重要,張國恩將人力資源發展與知識管理策略結合到數位學習中,並協助台灣上市企業發展內部的數位化訓練系統與建立企業數位大學。

Speech Title:
The Future of Education: New Space, New Knowledge and New Ontology

Professor Chen Li
陈丽教授

Vice President, Beijing Normal University
北京师范大学副校长


 
Speech Abstract

Prof. Li Chen will deeply elaborate how cyber space is transforming education on essence in three aspects. Firstly, Prof. Chen will explain the impact on education of disruptive technology. The cyberspace is a kind of disruptive technology which is an information space with different characteristics from physical space and social relation space. Now cyber space is transforming from two spaces to three spaces. Secondly, Prof. Chen will issue that in the cyber space knowledge is extending to all kind of experience and different from traditional knowledge the book. Prof. Chen will present her research findings on knowledge in the cyberspace. Thirdly, Prof. Chen will issue that education ontology is changing to connection. Prof. Chen is going to present the experimental study on cMOOC. At the end of the speech, Prof. Chen will call on the researchers in education technology to pay attention on revealing new foundation of education during applying new technology into education.

Speaker Bio
Prof Li Chen a PhD supervisor. She is vice president of Beijing Normal University. She is the leader of master program and PhD program of Distance Education in Beijing Normal University. Her research is mainly focusing on Education Transformation by Internet, online teaching & learning, and internet plus education strategy. She is deep engaged in policy consulting in Distance Education and lifelong learning. She has authored and published more than 10 books and 100 papers.

陈丽,博士、博士生导师。现任北京师范大学副校长。陈丽是北京师范大学远程教育硕士点和博士点的学科带头人。陈丽教授的主要研究领域为:1、互联网推动教育变革的趋势;2、在线教育教与学的规律;3、“互联网+教育”战略。陈丽教授是中国终身教育和远程教育领域的重要咨询专家。她已经出版了十余部著作和百篇以上的学术论文。

Speech Title:
Awarding Skill Improvements based on Behaviour Pattern Extraction and Analysis

Professor Maiga Chang
張明治教授

Full Professor, Athabasca University, Canada
 

Speech Abstract
Educational games and gamification learning systems usually provide learners rewards when they have progress on solving learning quests and/or doing learning activities. But how to give learners an appropriate reward that reflects the efforts they have taken and the skill improvements they have made? This talk will start with the showcases of couple of educational games that can help learners improve their meta-cognitive skills (e.g., problem solving, associative reasoning, evaluation and accuracy, and planning and organiz ation) and language speaking skill. These educational games record learners actions taken in the games and give learners points, virtual currency and virtual items to award their learning achievements and progress (i.e., skill improvements). This talk will then use the real game-play data collected from a commercial mobile educational game as example to explain the process of identifying and extracting learners' bahaviour patterns and calculating a learning quest/activity's general difficulty for most of learners as well as its difficulty for the particular learner. At the end of the process, the educational games and gamification learning systems is capable of awarding the learners proper rewards based on their efforts, improvements, and achievements.

Speaker Bio
Dr. Maiga Chang is a Full Professor in the School of Computing Information and Systems at Athabasca University, Canada. His research mainly focus on game-based learning, training and assessment, learning analytics and academic analytics, intelligent agent technology, etc. He is Chair (2018~2023) of IEEE Technical Committee of Learning Technology (TCLT), Chair (2021) of Educational Activities Committee & Awards/Recognition Committee, IEEE Northern Canada Section, and Secretary and Treasurer of International Association of Smart Learning Environments (IASLE)(2019~). He also serves as Executive Committee member for IEEE Computer Society Special Technical Communities (2021), Asia-Pacific Society for Computers in Education (APSCE)(2017~2024) and Global Chinese Society for Computing in Education (GCSCE)(2016~2021).

Dr. Chang is editor-in-chief of Journal of Educational Technology & Society (an Open Access SSCI journal), International Journal of Distance Education Technologies (an ESCI, SCOPUS, EI journal), and Bulletin of Technical Committee of Learning Technology (an Open Access ESCI journal). He serves as a Steering Committee member for International Conference on Intelligent Tutoring Systems (ITS)(2020~), program chair of International Conference on Smart Learning Environments (2015, 2018~2020), program committee chair of International Conference on Intelligent Tutoring Systems (2019), executive chair of inaugural English Paper Track of 24th Global Chinese Conference on Computers in Education (2020), IPC Coordination chair of International Conference on Computers in Education (2019). He has given more than 110 talks and lectures and (co-)authored more than 227 edited books, book chapters, journal and international conference papers.