[on behalf of Andrew Lan]
Call for Papers: KDD Workshop on Advancing Data with Education
IMPORTANT DATES
- Paper submission deadline : May 26, 2017
- Author notification: June 16, 2017
- Final version of accepted submissions: June 30, 2017
- Final workshop schedule: June 30, 2017
- Workshop: Aug 14, 2017
Please send your submissions via email to edu-kdd-2017@xxxxxxxxxxxxxxxx
Questions about the workshop can be sent to edu-kdd-2017@xxxxxxxxxxxxxxxx
WORKSHOP SUMMARY
The KDD 2017 Workshop on Advancing Education with Data will be held in
conjunction with the Knowledge Discovery and Data Mining conference on Aug
14, 2017 in Nova Scotia, Canada. The workshop will bring together data
scientists and educators together to stimulate research in the
interdisciplinary field of data science for education. At this year's
workshop, we are highlighting the following areas of interest: (1) Lifelong
learning, (2) Assessments (3) Learning Analytics and Personalization and
(4) Infrastructure.
More details about the workshop can be found below, or on the workshop
website: http://ml4ed.cc/2017-kdd-workshop/
PAPER SUBMISSION
We welcome submissions with either results that have not been published
previously or a summary of the authors' previous work that has been
recently published or is under review in another conference or journal. We
also encourage authors to submit extended abstracts and work-in-progress
papers with only preliminary results.
Submissions will be judged on their novelty and potential impact in the
emerging field of machine learning for education. Submissions should follow
the regular KDD paper format; there are no page limits. Papers submitted
for review need not be anonymized. Accepted papers will be made publicly
available on the workshop website, since there will be no official
proceedings. Accepted papers will be presented either as a talk or a
poster.
For more information about the KDD 2017 conference, please visit
http://www.kdd.org/kdd2017/
Looking forward to seeing you in Nova Scotia, Canada
Andrew Lan (Princeton University)
Christopher G. Brinton (Zoomi)
Jiquan Ngiam (Coursera)
Mung Chiang (Princeton University)
Richard Baraniuk (Rice University)
Roshan Sumbaly (Coursera)
Shivani Rao (LinkedIn)
------------------------------
WORKSHOP DETAILS
Online learning platforms have grown tremendously in recent years, having
an impact from K-12 to lifelong learning. In the classroom, educators are
starting to use technology to adjust their teaching methods for better
personalization. In companies, employers are leveraging online learning
platforms for the delivery of training programs that enable employees to
gain skills necessary for their jobs. Professionals are leveraging online
learning applications to stay up to date with the skills required to stay
relevant in the dynamic job market.
The data collected through these technologies presents a golden opportunity
to develop data-driven methods to improve education. We can now study the
impact of online learning platforms on lifelong learners, including those
from non-traditional backgrounds. Improving evaluation methods can impact
both skills assessment and measure learning efficacy. Personalization can
help make learning more efficient by tailoring to each learner’s individual
background and goals.
For this year’s workshop, we are highlighting the following areas:
-
Lifelong learning: In the past decade, technological advances have made
the job market more dynamic. The skills one needs to stay relevant in a job
market is constantly changing. This creates a growing incentive to engage
in lifelong learning, especially if you want to make a career transitions
or keep up with the new requirements of the job market. Encouraging
employees to learn at work can also help in employee retention and
increasing career satisfaction. In spite of all the benefits of lifelong
learning, there has been limited research on understanding these learners,
and the impact of learning at work for small or medium-sized businesses. We
have an opportunity to study the implications for employers, employees and
professionals, including career growth, non-traditional hiring, demographic
implications, and the business impact.
- Assessments are a key aspect of formative learning and summative
evaluation. Formative assessments power adaptive learning systems and can
make learning more efficient, while summative assessments are important for
establishing a learner’s skills and abilities. In the online education
setting, it is important for us to have assessments that credibly assess
learners in a scalable manner. Data mining and machine learning methods
have been employed to assess the quality of assessments, auto-grade
assessment questions, and automatically provide quality feedback at scale.
- Learning Analytics and Personalization: The abundance of online
learning content, and learning data collected about learners as they
interact with this content, presents the opportunity to analyze the process
of learning and personalize this process to meet each individual’s
preferences and needs. Recent studies have explored how learning behavior
(e.g., video-watching clickstream interactions) can be quantified in ways
that are predictive of performance (e.g., quiz scores), showing promise of
constructing low-dimensional user models that can give instructors useful
analytics about learners. The other side of learning analytics is
personalization where the information gathered about learners can be used
to recommend courses or videos or create personalized learning paths.
-
Infrastructure and Services for Learning: The introduction of scalable
learning applications has also pushed the boundaries of corresponding
infrastructure serving the need. These infrastructures need to serve data
sources of many format - graphs (knowledge and skill graphs, ontologies),
structured data (ratings data, multiple choice assessment data) and
unstructured data (video transcripts, forum discussion posts, learner
responses to open-form questions). Scalable services pose new operational
challenges while also presenting new solutions for learning. For example,
user generated content presents opportunities to solve interesting data
mining problems; we can utilize crowdsourcing algorithms to surfacing
popular and highly rated content, recommendations and search enhancements
and so on.
We hope this workshop will bring the community together to inspire new
ideas for data-driven innovations in education.
yours,
Andrew Lan
