Skip to content
EPSU Seminar – Predicting Stopout in MOOCS: Mining Behavioral Data June 1, 2015 Posted in: Blog, CETL, EPSU

banner-SEM150616

Organized by e-learning Pedagogical Support Unit, CETL

Speaker: Dr. Una-May O’Reilly, Principal Research Scientist, AnyScale Learning For All Group, MIT Computer Science and Artificial Intelligence Laboratory
Date : 16 June, 2015 (Tuesday)
Time : 12:45pm – 2:00pm
Venue : Room 321, Run Run Shaw Building

Abstract:

Understanding why students stopout will help in understanding how students learn in Massive Open Online Courses (MOOCs). In this seminar, Dr. Una-May O’Reilly will describe how she and her research group build accurate predictive models of MOOC student stopout via a scalable, prediction methodology, end to end, from raw source data to model analysis. They attempted to predict stopout for the Fall 2012 offering of MIT’s 6.002x.

This involved the meticulous and crowd-sourced engineering of over 25 predictive features extracted for thousands of students, the creation of temporal and non-temporal data representations for use in predictive modeling, the derivation of over 10 thousand models with a variety of state-of-the-art machine learning techniques and the analysis of feature importance by examining over 70,000 models. They found that stopout prediction is a tractable problem. Their models achieved an AUC (receiver operating characteristic area-under-the-curve) as high as 0.95 (and generally 0.88) when predicting one week in advance. Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks’ data, the models attained AUCs of ~0.7.

About the Speakers:

Dr. Una-May O’Reilly (http://people.csail.mit.edu/unamay/) leads the AnyScale Learning For All (ALFA) group (http://groups.csail.mit.edu/ALFA) at Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory. ALFA focuses on scalable machine learning, evolutionary algorithms, and frameworks for knowledge mining, prediction and analytics. She received the EvoStar Award for Outstanding Achievements in Evolutionary Computation in Europe in 2013 and serves as Vice-Chair of ACM Special Interest Group for Genetic and Evolutionary Computation (SIGEVO).


Miss Carmen Cheung
Email: carmen.cheung@hku.hk.

HKU04x: Making Sense of News – Sneak Preview 8 May 29, 2015 Posted in: Blog, edX, HKUx, JMSC, MOOC

We need to take note of our own biases before accusing news reports and/or news organizations of being biased.
Enroll in this free massive open online course now

Click here if you cannot access Youtube

Learn more: Sneak Preview 7 / Sneak Preview 6 / Sneak Preview 5 / Sneak Preview 4 / Sneak Preview 3 / Sneak Preview 2 / Sneak Preview 1 / Trailer

EPSU Seminar – Education 3.0: How Our Learning World is Changing May 22, 2015 Posted in: Blog, CETL, EPSU

banner-SEM140926

Organized by e-learning Pedagogical Support Unit, CETL

Speaker: Professor Curtis Bonk (Professor of Instructional Systems Technology, Indiana University)
Date : 5 June, 2015 (Friday)
Time : 12:45pm – 2:00pm
Venue : Room 321, Run Run Shaw Building (registration is capped at 60 due to room capacity)

During the past few years, learning has become increasingly collaborative, global, mobile, modifiable, open, online, blended, massive, visually-based, hands-on, ubiquitous, instantaneous, and personal. This is the age of Education 3.0 where learning is about playful and highly engaged design where learner creation of products is the new norm, often with the use of digital media. We humans tinker, invent, and express ourselves, and we find meaning in our playful pursuits. Fortunately, we are living in an age of educational resource abundance where passion, play, purpose, and freedom to learn take precedence over the more mind-numbing traditional information reception models of learning.

Instructors and experts are most effective as curators, counselors, consultants, concierges, and cultivators of student learning. These are the new instructional “C” words; gone are words like learning coercion, credit management, and fixed notions of correctness. Education 3.0 instructors are the ones who foster students’ autonomy and self-directed learning pursuits while, simultaneously, offering insightful guides and timely scaffolds where and when appropriate.

Attend this talk and find out how Education 3.0 will impact instructors and students, and how, in turn, we all can significantly impact it.

About the Speakers:

Dr. Curtis Bonk

Dr. Curtis Bonk is Professor of Instructional Systems Technology at Indiana University. A prolific author and internationally known speaker, he has published more than 300 articles and books on e-learning and has given more than 1,200 talks on many topics related to learning technologies and human learning.

Dr. Bonk received the CyberStar Award from the Indiana Information Technology Association, the Most Outstanding Achievement Award from the US Distance Learning Association, and the Most Innovative Teaching in a Distance Education Program Award from the State of Indiana. From 2012 to 2015, Bonk was named annually by Education Next and listed in Education Week among the top contributors to the public debate about education from more than 20,000 university-based academics. In 2014, he also was named the recipient of the Mildred B. and Charles A. Wedemeyer Award for Outstanding Practitioner in Distance Education.

His books have been translated into multiple languages and used internationally. These include The World Is Open: How Web Technology Is Revolutionizing Education (2009), Empowering Online Learning: 100+ Activities for Reading, Reflecting, Displaying, and Doing (2008), The Handbook of Blended Learning (2006), and Electronic Collaborators (1998). His latest book, Adding Some TEC-VARIETY: 100+ Activities for Motivating and Retaining Learners Online (2014), is freely available to download as an eBook at http://tec-variety.com/. His next book with Routledge, MOOCS and Open Education Around the World, will be out in June 2015.


Miss Carmen Cheung
Email: carmen.cheung@hku.hk.

Berkeley’s MOOC Experiment, a public lecture by Armando Fox May 21, 2015 Posted in: edX, HKUx, MOOC

Message from Faculty of Engineering

Presentation available here

Abstract
berkThis lecture will discuss how Berkeley has been performing relative to its MOOC goals: what has worked well, what they perhaps should have done differently or what they wish they were doing better, what challenges they face next, how MOOCs have affected classroom learning and teaching, and what their future might be at Berkeley. They continue to believe that the new momentum in online education is a strategic and permanent change for universities, even if that change ultimately takes a very different form than what the original MOOC creators envisioned.

Date: May 26, 2015 (Tuesday)
Time: 6:30 p.m. – 8:00 p.m.
Venue: Lecture Theatre A, Chow Yei Ching Building, The University of Hong Kong,
Pokfulam Road, Hong Kong
Speaker: Professor Armando Fox
Charge: Free registration

About the Speaker
Armando Fox is a Professor in Berkeley’s Electrical Engineering & Computer Sciences Department and the Faculty Advisor to the UC Berkeley MOOCLab. With his colleague David Patterson, he co-designed and co-taught Berkeley’s first Massive Open Online Course on “Engineering Software as a Service”, offered through edX, through which over 10,000 students in over 120 countries have earned certificates of completion. He also serves on edX’s Technical Advisory Committee, helping to set the technical direction of their open MOOC platform. His current research in online education includes automatic grading of students’ computer programs for style and improving engagement and learning outcomes in MOOCs.

Those interested in attending are requested to register online before noon, May 22, 2015.

For inquiries, please contact us by email at enggfac@hkucc.hku.hk or by phone at 2859 2803.