1.

MAIN DESCRIPTIONS
A. What is Learning Analytics?
According to a report that is published for United States Department of Education by
Bienkowski, M., Feng, M., & Means, B. (2012), it will be possible to track these features
with Learning Analytics: the situation of the students in the class, the average time that
they spend on a specific topic, students' favorite sections, the students who might need
additional support from the instructors, at-risk students' performance, study interruptions
and when the students interrupt. Some studies show that Learning Analytics can track
students and help teachers to make a valid decision about their students. Purdue
University has also created a system called Course Signals which is used in different
academic programs to provide messages about students academic performance before
the course has ended.
B. Learning Analytics & Educational Big Data
The current interest in learning analytics reflects wider interests in Big Data and
Educational Data Mining (EDM). Big data has been described is an all-encompassing
term for any collection of data sets so large and complex that it becomes difficult to
process them using traditional data processing applications whereas Educational Data
Mining (EDM) describes a research field concerned with the application of data mining,
machine learning and statistics to information generated from educational settings.
The interest in learning analytics reflects the increased use of analytics in other sectors.
Supermarkets, for example, analyze data on purchasing patterns, effectiveness of
marketing campaigns, etc. in order to target spending and manage stock levels. It has also
been suggested that analytics helped Germany win the 2014 World Cup [8]. However,
the use of analytics in a learning context poses challenges which are not applicable in
other cases. A further FAQ will explore such challenges in more detail.

According to George Siemens and Phil Long (2011), big data is a term used to describe
the new context of abundance. The McKinsey Global Institute defines big data as
datasets whose size is beyond the ability of typical database software tools to capture,

store, manage and analyze. In response to the limitations of existing data-management

techniques, a new breed of technologies (e.g., Hadoop), databases, and techniques (e.g.,
data-mining or knowledge discovery in databases) has been developed.
C. Learning Analytics & Academic Analytics
In colleges and universities, the data focus is increasingly expressed using the term
learning analytics. Though still a young concept in education, learning analytics already
suffers from term sprawl. The ubiquity of the term analytics partly contributes to the
breadth of meanings attached to it. For our purposes here, a reasonable definition of
learning analytics will help to guide discussion and frame activities.
According to the 1st LAK conference:
Learning analytics 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.
Academic analytics, in contrast, is the application of business intelligence in education
and emphasizes analytics at institutional, regional, and international levels.
Learning analytics is more specific than academic analytics: the focus of the former is
exclusively on the learning process, as detailed in Table 1. Academic analytics reflects
the role of data analysis at an institutional level, whereas learning analytics centers on the
learning process (which includes analyzing the relationship between learner, content,
institution, and educator).

The distinction of academic analytics as similar to business intelligence raises the need
for a model or stage of learning analytics development.

1. Course-level: learning trails, social network analysis, discourse analysis

2. Educational data-mining: predictive modeling, clustering, pattern mining
3. Intelligent curriculum: the development of semantically defined curricular resources
4. Adaptive content: adaptive sequence of content based on learner behavior,
recommender systems
5. Adaptive learning: the adaptive learning process (social interactions, learning
activity, learner support, not only content)

D. Components of Learning Analytics

Abelardo Pardo created a model to explain different stages of Learning Analytics and
what kind of questions need to be asked in those stages.
Capture
What data is being collected?
How frequently is the data collected?
Where is the data going to be stored?
Which format is going to be used to represent all events?
Are the observations securely stored?
Tracked behaviors and tracking methods
After current papers are specifically investigated for the behaviors that Learning
Management Systems track. The behaviors are the key factors on Learning Analytics
because they help the teachers what has changed on the background of the students.
The behaviors are already tracked by some Learning Management Systems and
tracking methods are listed:
According to You, J. W. (2016), these behaviors are tracked:

Time Management

Student Engagement

Assignment submission date

Frequency of visit

Proof of reading course material

According to Firat, M. (2016), these behaviors are tracked:

Time spent on LMS

The tools that the students used in the LMS

The specific time period that student spent on LMS was examined.

History of pages visited

According to Wu et. al. (2013), these behaviors are tracked:

Enhance students engagement

The activeness of students' engagement

Report
Who will receive the reports?
How frequently?
What kind of information needs to be reported?
How will the reports be accessed?
Predict
Which aspects of the experience need to be predicted?
Which factors can be used as input for the prediction algorithms?
What kind of prediction technique will be used?
How is the accuracy of the prediction going to be measured?
How are the predictions reported to the stakeholders?
Act
What actions are considered?
How are the actions deployed in the learning environment?
Refine
Are the data sources appropriate? Are the storage and access requirements for
the data appropriate?
Are the produced reports useful? Are they reaching the appropriate
stakeholders?
Are the prediction algorithms adequate? Are the predictions useful? Is the
accuracy appropriate?
Should the set of actions be revised? Are the actions properly deployed?

2. IMPLIMENTATION OF LEARNING ANALYTICS

A. The Value of Analytics for Higher Education & Who are the Key
Beneficiaries
Analytics spans the full scope and range of activity in higher education, affecting
administration, research, teaching and learning, and support resources. The
college/university thus must become a more intentional, intelligent organization, with
data, evidence, and analytics playing the central role in this transition.
How do big data and analytics generate value for higher education?
I.

They can improve administrative decision-making and organizational resource

allocation.

II.

They can identify at-risk learners and provide intervention to assist learners in
achieving success. By analyzing discussion messages posted, assignments
completed, and messages read in LMSs such as Moodle and Desire2Learn,
educators can identify students who are at risk of dropping out.

III.

They can create, through transparent data and analysis, a shared understanding of
the institutions successes and challenges.

IV.

They can innovate and transform the college/university system, as well as

academic models and pedagogical approaches.

V.

They can assist in making sense of complex topics through the combination of
social networks and technical and information networks: that is, algorithms can
recognize and provide insight into data and at-risk challenges.

VI.

They can help leaders transition to holistic decision-making through analyses of

what-if scenarios and experimentation to explore how various elements within a
complex discipline (e.g., retaining students, reducing costs) connect and to
explore the impact of changing core elements.

VII.

They can increase organizational productivity and effectiveness by providing upto-date information and allowing rapid response to challenges.

VIII.

They can help institutional leaders determine the hard (e.g., patents, research) and
soft (e.g., reputation, profile, quality of teaching) value generated by faculty
activity.

IX.

They can provide learners with insight into their own learning habits and can give
recommendations for improvement.

Who are the Key Beneficiaries?

The key beneficiaries of learning analytics include:

Institutional administrators taking decisions on matters such as marketing

and recruitment or efficiency and effectiveness measures.

Individual learners to reflect on their achievements and patterns of behavior

in relation to others.

Teachers and support staff plan supporting interventions with individuals and
groups;

Functional groups such as course teams seeking to improve current courses

or develop new curriculum offerings.

B. Dashboards
Learning analytics 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 (Siemens & Gaevi, 2012). Learning analytics is
mainly used in higher education. The following abbreviations are used for each of the
institutions and their associated case studies in higher education:
i.

Purdue - Traffic lights and interventions: Signals at Purdue University

ii.

NYIT - Identifying at-risk students at New York Institute of Technology

iii.

CSU - Fine grained analysis of student data at California State University

iv.

OU - Developing an analytics mind set at the Open University

Dashboards, Move beyond LMS, and Data Visualization

In the cases using predictive analytics, the output is commonly a dashboard or alert
system for staff with responsibility for supporting students. Many of these work in realtime on a daily or weekly cycle to identify students at risk of attrition, so staff can make
7

proactive interventions to support those students. Interventions are usually initiated by an

email or text message from staff to student, although some systems enable staff to put
indicators onto the students home page. Generally, proactive support from staff is more
effective than waiting for students to ask for help. There are, however, some issues
reported, such as students who appeared to be immune to intervention and others who
feel that interventions are demotivating or confusing, especially when communicated
multiple times across a range of media (Purdue).

However, complex data visualizations, dashboards and other support for learners may not
be necessary. Marists experience of directing at-risk students to a sophisticated support
environment suggests that simply making them aware that they are at risk may suffice.
Apparently confirming that a simple notification may be all that is required, at Purdue it
has been found that students who use Signals seek help earlier and more frequently. At
Purdue, students are given feedback through traffic lights, however human mediation is
considered important as well, though: messages are tailored by the instructors.

C. Moving beyond the LMS

Analytics from LMSsor VLEs (Virtual Learning Environments), as they are known in
Europe)offers one source of data for predicting the success of learners. Morris,
Finnegan, and Wu compared basic activities related to LMS participation (e.g., content
pages viewed, number of posts) and duration of participation (e.g., hours spent viewing
discussion pages and content) in LMSs and found significant differences between
withdrawers and successful completers, concluding that time spent on task and
frequency of participation are important for successful online learning.16 Leah P.
Macfadyen and Shane Dawson advocate for early-warning reporting tools that can flag
at-risk students and allow instructors to develop early intervention strategies.
LMSs have been adopted as learning analytics tools because the data captured is
structured and reflects the learners interaction within a system. But distributed networks
and physical world interactions present additional challenges for analytics. For example,
most LMS analytics models do not capture activity by online learners outside of an LMS
8

(i.e., in Facebook, Twitter, or blogs). Similarly, most analytics models do not capture or
utilize physical-world data, such as library use, access to learning support, or academic
advising. Mobile devices such as smartphones and tablets/iPads offer the prospect of
bridging the divide between the physical and digital worlds by capturing location and
activity. Similarly, clickers in classrooms can be integrated with data from learners
activity in online environments, providing additional insight into factors that contribute to
learners success.
Massive Open Online Courses (MOOCs), which occur in decentralized, distributed
teaching and learning networks, offer another challenge. Online social media monitoring
tools (e.g., Radian6) and reputation or influence monitoring tools (e.g., Klout) may
provide educators with a model for analytics in such networks, in which activity is
distributed across multiple sites and multiple identities.

D. Intelligent Curriculum
It is not sufficient to treat big data and analytics as useful only for evaluating what
learners have done and for predicting what theyll do in the future. Analytics in education
must be transformative, altering existing teaching, learning, and assessment processes,
academic work, and administration.
When analytics is applied to curricular resources, the traditional view of courses is
disrupted. The knowledge, attitudes, and skills required in any domain can be rendered as
a network of relations. The semantic web and linked data are partial instantiations of this
concept. Knowledge domains can be mapped, and learner activity can be evaluated in
relation to those maps. Instead of being an end of course activity, assessment is
performed in real time as learners demonstrate mastery of important concepts or ideas.
Learning content is not provided in a packaged textbook but is rendered or computed on
the fly, providing each learner with resources relevant to his or her profile, learning
goals, and the knowledge domain the learner is attempting to master. This is the essence
of the success that has accompanied the development of the Khan Academy learning
modules, even with their simplistic, mastery-based approach.

E. Did it work?
According to Papamitsiou and Economides (2014):
Search terms identified 209 mature pieces of research work, but inclusion criteria limited
the key studies to 40 between 2008-2013.
SWOT Analysis of LA/EDM research
Strengths

Large volumes of available educational data increased accuracy of experimental

results.

Use of pre-existing powerful and valid algorithmic methods.

Interpretable multiple visualizations to support learners/teachers.

More precise user models for guiding adaptation and personalization of systems.

Reveal critical moments and patterns of learning.

Gain insight to learning strategies and behaviors.

Weaknesses

Misinterpretation of results due to human judgment factors - focus on reporting,

not decision.

Heterogeneous data sources: not yet a unified data descriptive vocabulary data
representation issues.

Mostly quantitative research results. Qualitative methods have not yet provided
significant results.

Information overload complex systems.

Uncertainty: are we ready yet? So far, only skilled teachers/instructors could

interpret the results correctly.

Opportunities

Use of Open Linked Data for data standardization and compatibility among
different tools and applications generalized platform development.

10

Multimodal and affective learning opportunities based on sophisticated metrics.

Self-reflection/ self-awareness/ self-learning in intelligent, autonomous and

massive systems.

Feed machine readable results from the LA/EDM procedures to other data-driven
systems for diving decision making.

Acceptance Model: e.g., perceived usefulness, goal expectancy, perceived

playfulness, trust, etc.

Threats

Ethical issues data privacy.

Over-analysis: the depth of analysis becomes profound and the results lack
generality. The over-granularity approaches so far might threaten the holistic
picture being explored; look at the tree and miss the forest.

Possibility of pattern misclassification.

Trust: contradictory findings during implementations.

11

Community of Inquiry and Online Learning Communities

Community of inquiry framework is a model that helps online learning communities
with the main three presences: Social presence, cognitive presence, and teaching
presence. Community of inquiry framework has been applied by Garrison et al. (2000)
to research on asynchronous learning environments by showing that learning occurs
within a community through the interaction within the collaborative learning.
Community of inquiry has helped the process of education with online learning
communities in the constructivist approach. Online learning communities have been
formed with separate individuals in different places for a common purpose with the
help of the Internet.
There is evidence that a sense of community can be created online, although this is not a
trivial challenge. It has also been shown that sense of community is significantly
associated with perceived learning. This framework has provided significant insights
and methodological solutions for studying online learning.

12

A. Social Presence
Social presence refers to the ability of participants to project themselves as "real" in
an online community through use of indicators like emotional expression, open
communication, and various means. Social presence is described as the ability to project
ones self and establish personal and purposeful relationships. The three main aspects
of social presence, as defined here, are effective communication, open communication
and group cohesion. It is essential that the group feels secure to communicate openly
and coalesces around a common goal or purpose for a community to sustain itself.
Example:
e.g. - portraying yourself as "real", enabling risk-free expression, encouraging
collaboration.
It is not all about making friends, it is about forming a community of friendly and
discerning individuals.

B. Cognitive Presence
Cognitive presence is a component of Community of Inquiry framework and refers to
the extent to which participants are able to construct meaning through critical
thinking and reflection. Cognitive presence is defined as the exploration,
construction, resolution and confirmation of understanding through collaboration
and reflection in a community of inquiry. Cognitive presence is defined in terms of a
13

cycle of practical inquiry where participants move deliberately from understanding the
problem or issue through to exploration, integration and application.
Example:
e.g. - exchanging information, connecting ideas, and applying new ideas.
Practice and assess the cognitive presence in the course using the practical inquiry
model, which consist of four steps.

14

C. Teaching Presence
Teaching presence is also one of the constructs of Community of Inquiry model. It refers
to selection, organization, designing, facilitation and direction of learning process
to reach meaningful and educationally worthwhile learning outcomes. The third issue
worth exploring is a validation issue. To be sure, validation of the community of inquiry
and its constructs is an important issue. However, the focus here is the teaching
presence construct and whether it has three distinct categoriesdesign, facilitation and
direct instruction.
Example:
e.g. - setting curriculum and methods, sharing personal meaning, focusing discussions.
Provide students enough guidance to facilitate learning without telling them how or
what to learn (exploration).

Relation with Learning Analytics:

Learning analytics can be used to collect data from students to track their
connectedness. For example, there is a one paper that examines students
characteristics. The purpose of current study is to identify the relationship between
adult learners characteristics in relation to age, gender, previous attendance to an
online course, the number of log ins per week, community of inquiry presences
consisting teaching presence, social presence, cognitive presence, online self-regulated
learning and its subscales including goal setting, task strategies, environment
structuring, time management, help seeking and self-evaluation in an online
instructional setting.

15