1. T4D
Frontiers of Engineering
for Development
Symposium:
Frontiers of Engineering
for Development Symposium
Session : Knowledge Economy
2. Learning System Development My Experiences
• HyperCAL : Developing Hypertext based Computer Aided
Learning System (1993-95)(funded by University Grants
Commission)
• A system meant for Post Graduate Level Students
Continuous Assessment based on quizzes
• Internet Safari : A Project to develop interactive content
for underprivileged school children towards digital
inclusion( 2009-10)( Funded by National Internet
Exchange of India –NIXI)
• The Content was interactive and story based on a
character that we developed called – Tobo
• The kids were tested on a quiz
4. Did we Transform Learning ?
Source : McDaniel, M. (2011). 21st Century Teacher.
5. Session : Knowledge Economy
Chair :
Shalini Urs, MYRA School of Business, Mysore, India
Speakers :
1. Prof. Ifiok Otung,
University of South
Wales
2. Prof.Andrew McBride,
University of Glasgow
3. Dr. Prasad Ram,
Gooru
6. Four Pillars (World Bank)
Economic Incentives and
Institutional Regime
Innovation and
Technological Adoption
Education
and Training
ICT Infrastructure
Knowledge Economy
7. Setting the Context
• The phrase knowledge economy was
popularised by Peter Drucker in his
book The Age of Discontinuity (1969)
• Knowledge is recognised as the driver
of productivity and economic growth,
leading to a new focus on the role of
information, technology and learning
in economic performance.
• Represents fuller recognition of the
place of knowledge and technology in
modern economies.
8. Goals of Knowledge Economy
“A commitment of individuals,
organizations, and the economy at
large to continually learn and to
increase their skills and expertise, to
foster innovation”
9. Digital Transformation and the Knowledge Economy
• The Digital Transformation enhanced access
to and availability of learning resources, it is
not clear whether the goals hae been met
• Over the years, we have witnesed
technology expanding accessibility,
availability, and achievability of
"knowledge”
• The web 2.0 technologies turned knowledge
economy into a shared economy (the
Wikinomics Model) (Gig economy) ( Shared
Economy)
• We have successfully managed the
"knowledge management" challenges, but
we are still far away from managing
Learning Activities and Outcomes
10. Transformation of diverse experiences
• Amazon transformed the Shopping
Experience
• Uber disrupted and transformed
the cab hailing experience
• Tesla has transformed the driving
and whole car driving experience
Two major
changes :
Personalization
and Adaptation
Through
analytics
11. How do we transform Learning ?
• A diverse array of learning activities and
practices add value to the learning process
and but if we can develop a system for
tracking the learning by an outcome based
method and platform, we have won half the
battle.
• Only-digital learning experiences have
severe limitations in learning. Offline
activities such as projects and group
discussions have an essential pedagogic
value.
• Classroom instructional practices can make
substantial contributions to learning
outcomes.
12. What we need …
• Real-time
interventions based
on how students
are learning or
persoanlising what
they have learned
• We ought to be
able augment
Classroom practices
with real-time data.
13. Transforming Learning
• If we can show positive outcomes for everyone,
the rest of the ecosystem will coordinate to make
devices and broadband happen.
• For students to have high outcomes, we need to
go beyond the curriculum to develop non-
cognitive skills. Teachers and peers most
efficiently do these.
• Relying on MCQs (multiple choice questions)
does not provide “quality of evidence.”
• How do we score essays, proofs, etc.?
• Rubric-scored questions with peer grading or
may be crowd-sourced grading
15. Educational Data Mining and
Learning Analytics
• The goal of learning
analytics is to “enable
teachers and schools to
tailor educational
opportunities to each
student’s level of need
and ability.”
Analytical models process and display the
data to assist faculty members and school
personnel in interpretation.
16. What is Learning analytics ?
It is the measurement,
collection, analysis and
reporting of data about
learners and their contexts,
for purposes of
understanding and
optimizing learning and the
environments in which it
occurs.
17. Learning Analytics
“Interpretation of a wide range of data produced
by and gathered on behalf of students to assess
learning progress, predict future performance, and
spot potential issues.
Data are collected from explicit student actions,
such as completing assignments and taking exams,
and from tacit actions, including online social
interactions, extracurricular activities, posts on
discussion forums, and other activities that are not
directly assessed as part of the student’s
educational progress.
19. User knowledge modeling
Questions
• What content does a student Know
? (e.g., specific skills and concepts
or procedural knowledge and
higher order thinking skills)
One Example
• A popular method for
estimating students’
knowledge is Corbett and
Anderson’s knowledge
tracing model (Corbett
and Anderson 1994), an
approach that uses a
Bayesian-network-based
model for estimating the
probability that a student
knows a skill based on
observations of him/her
attempting to perform
the skill.
What data is needed ?
Student’s responses (correct,
incorrect, partially correct, time
spent before responding to a prompt
or question, hints requested,
repetitions of wrong answers, and
errors made
20. User behavior modeling
• Questions
• What do patterns of
Student responses
behavior mean for their
learning?
• Are students
motivated?
Example :
Students Gaming
Behavior-- attempts
to game the system (
for example clicking
until you get the
correct answer )
21. User/Learner Profiling
• Learner Profiles document the ways a student best learns.
Learner Profiles typically include a broad range of data:
demographic data, data about student interests, learning
preferences, descriptions of the learning environment student
prefer, inter- and intra-personal skills, existing competencies
and those that need to be developed (in the personal, social-
emotional, academic and career arenas).
• Profiles may be compiled through diagnostic data, intake
inventories, conferences with students and family members,
analysis of previous school records, and school/classroom
observation.
• Profiles are dynamic documents, that should change in both
the short- and long-term: students' interests will change, they
will become competent in new areas, etc. Changes should all
be documented in the Profile.
22. Domain Modeling
• A domain model is to be created to represent
the key concepts that make up a subject or
topic area like mathematics or art history (i.e.,
domains).
• The domain model also identifies the
relationships among all the key concepts or
units of study.
• Research in domain modeling in educational
data mining and learning analytics investigates
how learning is affected by differences in how
a topic is divided into key concepts at a
particular level of generalization.
23. Experiences in Data Capturing
• I use Moodle as a LMS in our School
• We can use many of the plugins available for
Learning Analytics
• Logs and Live Logs are some examples of
Learning Analytics
41. Analytics Graphs
This plugin provides five graphs that may facilitate
the identification of student profiles. Those graphs
allow the teacher to send messagens to users
according to their behaviour inside a course.