=Paper=
{{Paper
|id=Vol-2209/paper1
|storemode=property
|title=Detection of Online Learning Activity Scopes
|pdfUrl=https://ceur-ws.org/Vol-2209/paper1.pdf
|volume=Vol-2209
|authors=Syeda Sana E. Zainab,Mathieu D'Aquin
|dblpUrl=https://dblp.org/rec/conf/ectel/Zainabd18
}}
==Detection of Online Learning Activity Scopes==
https://ceur-ws.org/Vol-2209/paper1.pdf
Detection of Online Learning Activity Scopes
Syeda Sana e Zainab1 and Mathieu D’Aquin1
Data Science Institute, National University of Ireland Galway, Ireland
{firstname.lastname}@insight-centre.org
Abstract. During last ten years, online learning has been on the as-
cent as the advantages of access, accommodation, and quality learning
are beginning to take shape. A key challenge is to identify learning ac-
tivities and recognize how they participate in the learner’s progress. In
this paper, we look at the way this problems becomes even more chal-
lenging when considering the full set of online activities carried out by a
learner, as compared to what is achieved on specific online platforms that
are dedicated to learning. We in particular show how the integration of
linked data-based information can help resolve the issue of representing
activities for the purpose of identifying the key topics on which a learner
is focusing, in a hierarchical clustering method. We apply this approach
in the context of the AFEL project, and show how it performs in realistic
use cases of an online learner’s profile, comparing general browsing with
the use of a dedicated learning platform.
Keywords: eLearning· Text mining· Hierarchical Clustering
1 Introduction
Online learning, often called “eLearning”, is a new class of learning that has been
flourishing during the last ten years, following the growing adoption of eLearning
in universities, schools, and companies. Online learning provides a convenient
environment where instructors and students may access the course, study, and
perform interactive learning activities with fewer time and space restrictions.
However, the analysis of such online learning activities often requires systems
and applications using learning analytics and data mining approaches. In many
cases learning activities which are contributing to the learner’s progress are not
well detected and are outside of these systems and applications.
In the AFEL (Analytics for Everyday Learning) project1 , we aim to address
this challenge by defining a process for detecting online learning activities en-
riched with specific “topic-based” learning trajectories and visualize them in
an application that enables potential learners to reflect on their activities and
ultimately improve the way they focus their learning.
The aim is to apply this to both online platforms dedicated to learning and
to general online activities, showing how learning happens in everyday activities.
1
http://afel-project.eu
2 S. Sana et al. and d’Aquin et al.
Didactalia2 is the online social learning platform we use as a testbed. We can
directly connect to Didactalia through its API and retrieve metadata about its
resources, allowing us to classify them in different topics, and to assess their
value to the learning of the user.
However, when generalising this approach to multiple platform, we cannot
guaranty that a meaningful description will be available for the resource consid-
ered. To take an extreme case, we are testing the detection and assessment of
learning activities within the overall web browsing activities of a user. In this
case, we need to face issues related to the differences in scale and velocity of the
data we received. We also need to find ways to retrieve information that can help
understanding the content of resources and assess them with respect to learning.
In this paper, we describe a method to identify key areas in which users of
online resources are learning, by: 1- enriching the resources considered based
on linked data, 2- clustering activities using this enriched information, and 3-
identify the clusters that are most representative of the user’s learning through
learning indicators also using the enriched information.
2 Related Work
Research demonstrates that assessment of the student learning is a key to suc-
cess of any education system, and is “one of the main considerations separating
capable schools and instructors from incapable ones”[4]. This also applies to
online learning, e.g Helic et al. [10] contend that good online learning requires
monitoring of a student’s progress with the material and testing of the gained
information and aptitudes all the time. Various measurements enable educators
to monitor the student input, feedback, and progress towards goals and is crucial
in online education [16]. Few works have been done to analyze learning through
a social media [3] but they are more focused towards the learning perspective of
social network rather than detecting learning aspects in online activities. Some
researches consider the combination of semantic web technologies with learning
activities analysis [5,8], but they are more focused towards the integration of
data.
Ferguson and Buckingham Shum [7] proposed the concept of learning activ-
ities analysis to specifically capture the social interactions underlying the social
learning processes. Similarly, a model for mobile and ubiquitous learning envi-
ronments has been proposed by Aliohani and Davis [1] for the learning analysis.
A further action towards learning analysis methods which take into account the
amount of data produced by the learner’s activities both in formal and infor-
mal settings is offered by the semantic web [2], that pointed out the practical
educational benefits for teaching and learning. Some of the learning analytical
work has been focused on health care systems. Such systems [17,19] typically
employ sensors e.g. wearable sensors and visual sensors, collect a users activities
data such as eating or exercise and apply machine learning algorithms to identify
2
https://didactalia.net
Detection of Online Learning Activity Scopes 3
activities progress. A significant work have been done in applications and tools
development [9,20,11,13,12] for learning activities analysis. However these appli-
cations enable learners to track their progress on certain areas (games, music,
document writing etc) or communities (Players, Moodles etc).
Among the diverse works that have been proposed on the analysis of learning
activities, a few has been focused on scopes detection in online learning activi-
ties. Our work is focused towards the identification of online learning activities
scopes and develop an application that helps the learner in their online learning
progression.
3 Motivation: The AFEL Project
In several other areas than learning where self-directed activities are promi-
nent (e.g. fitness), there has been a trend in recent years following the tech-
nological development of tools for self-tracking. Those tools quantify a specific
user’s activities with respect to a certain goal (e.g. being physically fit) to enable
self-awareness and reflection, with the purpose of turning them into behavioral
changes. While the actual benefits of self-tracking in those areas are still debat-
able, our understanding of how such approaches could benefit learning behaviors
as they become more self-directed remains very limited.
AFEL is an European Horizon 2020 project which aim is to address both
the theoretical and technological challenges arising from applying learning ana-
lytics in the context of online, social learning. The pillars of the project are the
technologies to capture large scale, heterogeneous data about learner’s online
activities across multiple platforms (including social media) and the operational-
ization of theoretical cognitive models of learning to measure and assess those
online learning activities. One of the key planned outcomes of the project is
therefore a set of tools enabling self-tracking on online learning by a wide range
of potential learners to enable them to reflect and ultimately improve the way
they focus their learning.
Below is a specific scenario considering a learner not formally engaged in a
specific study program, but who is, in a self-directed and explicit way, engaged in
online learning. The objective is to describe in a simple way how the envisioned
AFEL tools could be used for self-awareness and reflection, but also to explore
what the expected benefits of enabling this for users/learners are:
Jane is 37 and works as an administrative assistant in a local medium-sized
company. As hobbies, she enjoys sewing and cycling in the local forests. She is
also interested in business management, and is considering either developing in
her current job to a more senior level or making a career change. Jane spends a
lot of time online at home and at her job. She has friends on Facebook with whom
she shares and discusses local places to go cycling, and others with whom she
discusses sewing techniques and possible projects, often through sharing YouTube
videos. Jane also follows MOOCs and forums related to business management,
on different topics. She often uses online resources such as Wikipedia and online
4 S. Sana et al. and d’Aquin et al.
magazines. At school, she was not very interested in maths, which is needed
if she wants to progress in her job. She is therefore registered on Didactalia3 ,
connecting to resources and communities on maths, especially statistics.
Jane has decided to take her learning seriously: She has registered to use
the AFEL dashboard through the Didactalia interface. She has also installed the
AFEL browser extension to include her browsing history, as well as the Facebook
app. She has not included in her dashboard her emails, as they are mostly related
to her current job, or Twitter, since she rarely uses it.
Jane looks at the dashboard more or less once a day, as she is prompted by a
notification from the AFEL smart phone application or from the Facebook app,
to see how she has been doing the previous day in her online social learning. It
might for example say “It looks like you progressed well with sewing yesterday!
See how you are doing on other topics...” Jane, as she looks at the dashboard,
realizes that she has been focusing a lot on her hobbies and procrastinated on the
topics she enjoys less, especially statistics. Looking specifically at statistics, she
realizes that she almost only works on it on Friday evenings, because she feels
guilty of not having done much during the week. She also sees that she is not
putting as much effort into her learning of statistics as other learners, and not
making as much progress. She therefore makes a conscious decision to put more
focus on it. She adds new goals on the dashboard of the form “Work on statis-
tics during my lunch break every week day” or “Have achieved a 10% progress
compared to now by the same time next week”. The dashboard will remind her
of how she is doing against those goals as she goes about her usual online social
learning activities. She also gets recommendations of things to do on Didactalia
and Facebook based on the indicators shown on the dashboard and her stated
goals.
While this is obviously a fictitious scenario, it highlights the key challenges
faced by the project. The one specifically addressed by this paper is the iden-
tification of the topics on which the learning of the user is mostly focusing, so
that the activities related to those topics can be assessed in the context of the
relevant learning scope.
4 Overview
Figure 1 provides a general view of the data architecture used in the AFEL
project. In summary, an external platform provides, through the POST API, a
stream of activities, including an identifier of the user performing the activity
u, the time at which the activity happen t, and a reference to the resource
being used as part of the activity r. The POST API will then both index those
activity descriptions, and call an internal service called the “Resource Indexer”,
which role is to obtain additional information about the resources being used
by the learner, and enrich them with information necessary for both detecting
3
http://didactalia.net
Detection of Online Learning Activity Scopes 5
Fig. 1. Overview of the AFEL data architecture.
the learning scopes (the topics on which they are learning) and in assessing
their learning progress within those scopes. Based on all those information being
stored and indexed, the role of the GET API is to retrieve them and provide
to the AFEL application all the relevant data for a given user, including the
activities performed, in which learning scope they belong, and indicators of how
much they contribute to the learning trajectory of the learner.
Although not the topic of this paper, a key challenge here is in identifying
the indicators that can support assessing the progress of a learner in a certain
learning scope. Based on theoretical work in educational psychology within the
AFEL project (see for example [15]), the approach taken is to try to recognize to
what extent encountering and processing a certain artifact (a resource) induced
learning, based on representing “frictions” that are bringing new knowledge or
new forms of knowledge to the learning. At the moment, we distinguish three
forms of “frictions”, leading to three categories of indicators of learning (see [6]):
– New concepts and topics: The simplest way in which we can think about
how an artifact could lead to learning is through its introduction of new
knowledge unknown to the learner. This is consistent with the traditional
“knowledge acquisition metaphor” of learning. In our scenario, this kind of
friction happens for example when Jane watches a video about a sewing
technique previously unknown to her. We call the indicator associated with
this form of friction coverage.
– Increased complexity: While not necessarily introducing new concepts, an
artifact might relate to known concepts in a more complex way, where com-
plexity might relate to the granularity, specificity or interrelatedness with
which those concepts are treated in the artifact. In a social system, the
assumption of the co-evolution model is that the interaction between indi-
6 S. Sana et al. and d’Aquin et al.
viduals might enable such increases in understanding of the concepts being
considered through iteratively refining them. In our scenario, this kind of
friction happens for example when Jane follows a statistics course which
is more advanced than the ones she had encountered before. We call the
indicator associated with this form of friction complexity.
– New views and opinions: Similarly, known concepts might be introduced “in
a different light”, through varying points of views and opinions enabling a
refinement of the understanding of the concepts treated. This is consistent
with the co-evolution model in the sense that it can be seen either as a widen-
ing of the social system in which the learner is involved, or as the integration
into different social systems. In our scenario, this kind of friction happens
for example when Jane reads a critical review of a business management
methodology she has been studying. We call the indicator associated with
this form of friction diversity.
While in the implementation of the AFEL application, all three indicators
are being used, we will here focus only on the first one, as the two others are
the subject of specific work. To simplify, we will therefore consider the problem
tackled as:
How to identify learning scopes in a stream of activities, where learning scopes
represent a set of activities that cover a particular topic by the learner?
Fig. 2. Overview of the method used for identifying learning scopes.
While there are many ways in which this question could be answered, we
here consider the key requirements that the method should equally work in cases
Detection of Online Learning Activity Scopes 7
where resources are already described with rich metadata (e.g. tags) and in cases
where we have no other information about the resources than their content. It
also needs to take into account the dynamic aspect of the scenario (that new
activities are constantly being added).
We therefore describe in the next sections the three main steps of the method
represented in Figure 2.
5 Enrichment
The goal of the enrichment phase of the process described in Figure 2 is to extract
from the resources used in learning activities information about their content,
in the case such information is not already available. Indeed, in many cases if
we focus on specific platforms, resources will be classified and associated with
subjects and topics. This is the case for example of Didactalia which associates
with each resource a set of tags, as provided by the users who contributed the
resources. Those tags can then be used to represent a general overview of the
content of the resource. However, when working with general online resources,
we cannot rely on the availability of such metadata.
Using named entity recognition is a common approach to this problem. By
extracting from the textual content of the resource key entities and concepts that
are being mentioned, we can build a profile of the resources that can potentially
be used to replace the tags available in existing platforms.
We use DBpedia Spotlight4 as an off-the-shelf named entity recognition tool.
The advantage of DBpedia spotlight is that, practically, it is open source and
can be deployed locally, removing the need to rely on an external service. This
is especially important in our scenario as we need to process thousands of po-
tentially large texts for each user. Since it is based on Wikipedia, in addition,
the vocabulary of entities being covered is very wide and domain-independent,
with millions of entities being recognizable on all sorts of topics.
The other advantage of DBpedia Spotlight is that the entity extracted are
part of the DBpedia Linked Dataset.5 DBpedia is a linked data version of
Wikipedia and, as such, also contains the taxonomy of categories of Wikipedia.
This is especially useful here since our goal is to group activities based on their
associated resources covering similar topics. To achieve this however, entities
extracted are insufficient. Indeed, resources might be on the same topic (e.g. ge-
ography) without mentioning the same entities. Nevertheless, if they are indeed
of the same topic, it is more likely that the categories of the entities mentioned,
or their super-categories, will overlap.
The goal of the generalization process is therefore to augment the profile
created by named entity recognition by adding the categories that relate to the
entities found through named entity recognition to the profile of each resource.
To make this efficient, it relies on an index of the “direct” categories of each
entity and on an index of the DBpedia category hierarchy. Each entity is then
4
https://github.com/dbpedia-spotlight/dbpedia-spotlight
5
http://dbpedia.org
8 S. Sana et al. and d’Aquin et al.
iteratively assigned categories at a higher level than its direct ones by climbing
up this hierarchy until a given level. This process is of course carried out offline,
with the online process only executing named entity recognition, and adding the
pre-computed set of categories to the entity.
It is important to note here that the profile of a resource in this case is richer
than the set of tags that might be available in online platforms. It is not only
larger (the number of entities and categories found will generally be bigger than
the number of tags manually used to describe a resource), it also contains more
information, as multiple mentions of a given entity are counted, and multiple
references to a category are also taken into consideration. In this way, if more
than one entity are related to a given category, this category will have a stronger
weight during the clustering phase.
6 Clustering
The objective of the enrichment method described above is to build a profile for
resources that the learner has been using that captures the key topics, so that
they could be grouped into general learning scopes. The next step is therefore to
cluster activities based on those profiles. Here too, there are many ways to cluster
based on the kind of resource profiles we have constructed in the previous step,
which very much represent vectors of term frequencies. However, considering the
nature of the scenario in which we are operating, we need to consider three key
requirements:
– The clustering cannot be static: As the building the learning scopes is to be
carried out from the stream of user activities, it obviously cannot be built
in advance.
– The clustering needs to be incremental : Very related to the previous re-
quirement, but adding that the clustering mechanism needs to be fast, the
approach is required to be incremental, i.e. new activities and resources need
to be added into an already constructed set of clusters, from previous activ-
ities and resources. It is also important that the set of clusters do not evolve
dramatically due to the appearance of new activities and resources.
– The number of clusters cannot be fixed in advance: Many clustering mecha-
nisms take as a given parameter the target number of clusters. However, this
should in our case be automatically set, since we cannot decide in advance
for every user how many topics they are learning about.
For those reasons, we adopted an incremental hierarchical clustering ap-
proach. Hierarchical clustering [14] is a method by which clusters are formed
by progressively grouping items, creating a hierarchy of larger and larger clus-
ters. One advantage of hierarchical clustering is that it creates many clusters
of different sizes and levels, from which we can select afterwards based on their
properties (see next section), rather than having to choose a number of clusters
in advance.
Detection of Online Learning Activity Scopes 9
However, the basic algorithm for hierarchical clustering assumes that the
whole set of items to clusters are available. We therefore adapt it so that it can
work incrementally, and fulfill our two first requirements. The basic algorithm
we use is described below and broad terms. It represents the function to add a
new item to an already existing cluster.
function add(item, clusterset)
if clusterset is empty then
c = new cluster([item])
insert c in cluster set
else
find c the cluster in clusterset most similar to item
nc1 = new cluster(concat(c, item))
nc2 = new cluster(item)
p = parent(c)
remove c from children of p
add nc1 as child of p
add c as child of nc1
add nc2 as child of nc1
By using this algorithm for every new items one after the other, a set of
clusters is built organized as a hierarchy. The advantage is that the clusterset
can be kept from one activity to the other, meaning that a new activity would
only have to be added to it, and will not be require large amounts of computation.
It is useful to note that
– The similarity measure used can vary. In our initial tests, we use an eu-
clidean distance on the frequency vectors of terms (entities and categories)
as obtained above. Further tests with other similarity measures (e.g. based
on a cosine distance over TF.IDF vectors) are being conducted, giving better
results.
– The creation of new a cluster computes a term frequency vector aggregating
the vectors of all included items using their average. Therefore, the similarity
is applied between those aggregated vectors and the original vector of the
item to be added.
It is also useful to mention that this approach is not guarantied to obtain
the same clusterset as one that would have applied hierarchical clustering in a
non-incremental, static manner. Methods exist to achieve better approximations
than the proposed algorithm (see e.g. [18]) but those tend to be computationally
expensive. Also, as mentioned above, an advantage of this approach is that the
clusterset only changes in a very localized manner, keeping the established struc-
ture mostly intact and is therefore less likely to lead to dramatically changing
results for the user.
10 S. Sana et al. and d’Aquin et al.
7 Cluster selection and labelling
The last step to be considered is the selection of the set of clusters of activities
that are most representative of the learner’s interests, and their labelling. Indeed,
we have obtained from the previous step a chusterset which is hierarchically
organised (it is, actually, a binary tree). The idea is to identify the ones that
seem to be most interesting from the point of view of the learning indicators
considered (see earlier description of the learning indicators).
We therefore start by ranking the clusters in the clusterset according to a
score. While not taking into account the hierarchy, an important aspect of this
score is that it takes into account the temporal aspects of activities. Indeed, if
taking into account only the coverage indicator, as described above, the idea is
to measure for each activity how many new concepts (entities and categories)
it introduces into each of the clusters as a proportion of the concepts already
present there from previous activities. Taking that into account, we can compute
the average coverage of each cluster based on the included activities, effectively
corresponding to a measure of how much, on average, an activity in this cluster
increases the coverage of the topics of the cluster. It is worth noting that, while
new activities (and therefore new clusters) affect the score of certain clusters
and, obviously, their ranking based on this score, this can still be achieved in-
crementally, i.e. we can update the scores of clusters based on new activities,
and update the ranking based on those changes without having to recompute it
every time.
The results of the previous step is a ranked clusterset rankedcl, sorted in
descending order of the score considered. The selection process from there can be
reduced to selecting non-overlapping clusters that are highly ranked. To support
the non-overlapping property, we exploit the hierarchical relationship that exist
between clusters from the hierarchical clustering process, i.e. selected clusters
should be taken from distinct branches of the tree as per the algorithm below:
function select(rankedcl) returns selected
foreach c in ranked
select = true
foreach s in selected
if c is a (direct/indirect) child/parent of s
select = false
if select
insert c in selected
This approach has the two advantages that, because of the non-overlapping
property of clusters being selected, we do not need to set a threshold for the
cluster score to be selected, since, once a cluster is selected, all overlapping
clusters are automatically removed from the candidate list. This means that the
results are a limited subset of all the clusters that are complementary in terms
of topic, and have the best coverage in score. This also means that clusters are
selected to represent learning activities, and further filters can be applied later
Detection of Online Learning Activity Scopes 11
based on other indicators to emphasise the clusters related mostly to learning
activities.
The final results of this phase are a set of selected clusters grouping similar
activities that have on average a good contribution to the coverage of the topic of
the cluster, and characterised by a verctor of term frequencies from the entities
and categories in DBpedia. The last step is to label those clusters. For this, we
take the simple approach to choose as label the entity or category in the vector
with the greatest weight as label for a given cluster.
8 Application in two case studies
In order to test and validate the method described above, we apply it in two
different scenarios with different sources of data. Those two scenarios actually
rely on the same application, and on the same architecture depicted in Figure 1,
in the context of the AFEL project. These scenarios however differ in the data
sources they consider. In one case, the activity data is taken from an online social
platform, Didactalia, where there is a limited amount of activities relating to well
described resources, and clearly associated with learning. In the other case, the
data is taken from the general browsing history of the user, generating much
more and much more frequent activities, associated to resources that have no or
very little metadata, and which are not necessarily directly related to learning.
Didactalia is an online, social learning platform. It includes more than 100,000
resources that are contributed and annotated by users, and shared within various
communities. The whole platform relies on linked data technologies, and enable
connecting resources with each other. We collect activity data from Didactalia
through using a javascript snippet similar in style to the one used by web analyt-
ics tools such as Google Analytics or Piwik. The information about the resources
are provided through an RDF-based API on the Didactalia platform.
The results of applying our application to Didactalia are shown in an example
in Figure 3. The application first shows the detected learning scopes for the user
in a world cloud depending on the indicators considered. Each learning scope
can then be further explored, showing specific indicators, recommendations, etc.
The detection of learning scopes here is therefore critical. While there are tens
of thousands of users or Didactalia, and we therefore collect millions of data
points over time, each user will only carry out between a few activities and in
the order of one hundred. The tags associated with the resources can be used
as the initial profile vector for each activity/resource, possibly in combination
with the entities and categories from DBpedia. Considering the low number of
activities, the complexity of the process is less critical, although it needs to be
handled for a large number of users. Also, compared to the second scenario, each
of the learning scopes is more or less guarantied to be related to learning, since
they only capture activities that are carried out on a learning platform.
On the other hand, the application of the our method to the user’s whole
browsing history (shown in an example in Figure 4) has to deal with a lot of
activities for each users (up to thousands per day), with very little overlap and
12 S. Sana et al. and d’Aquin et al.
Fig. 3. Application for Didactalia, using learning scope detection (right) and showing
learning indicators for a given learning scope (right).
not much description. The data in this case is collected through a specially
developed browser extension6 (compatible with browsers supporting web-ext).
The application functions very much in the same way, except that in this case the
learning scopes detected are much broader and have to be based on the entities
and categories from Dbpedia. In this case as well, the scale is much more of
an issue. The built hierarchical clusterset can have tens of thousands of nodes
for one user, and it would be unfeasible to rebuild it every time. It is therefore
important, as we have chosen to do, to update it incrementally every time a new
activity appears.
While the accuracy of the learning scope detection is subjective, the ap-
plications described above demonstrate that the proposed method, combining
incremental hierarchical clustering with activity profiles based on named entity
recognition and abstraction through DBpedia categories can indeed be applied
and adapts well to different contexts.
6
https://github.com/afel-project/browsing-history-webext
Detection of Online Learning Activity Scopes 13
Fig. 4. Application for the learner’s browsing history, using learning scope detection
(right) and showing learning indicators for a given learning scope (right).
9 Conclusion and Future Work
In this paper, we described a method that can be used to dynamically and
efficiently detect the main topics a user is learning about (the learning scopes)
that can be used on applications such as the ones developed in the AFEL project
that rely on varied datasets, from small well-described ones, to large and open
ones for which metadata is not available. This method is currently deployed in
real-case scenarios within the AFEL project, and an evaluation is being carried
out of the benefits they can generate with respect to the learning process of the
user, beyond the basic validation presented here through the two case studies
described.
Naturally, the proposed method currently suffers from a number of limita-
tions which we intend to address as part of our future work. In particular, the
named entity recognition method employed currently, as well as the methods to
compute the learning indicators used in the applications other than the one re-
lated to coverage, are currently designed only considering the English language.
14 S. Sana et al. and d’Aquin et al.
Alternatives and versions of the techniques and tools used are available for other
languages, but a language detection mechanism will be needed in order to be
able to direct the processing of a resource to the right version depending on the
main language of the textual component of that resource.
This also raises a clear other limitation, i.e. that our method is dedicated to
online resources which content is mainly textual. This restricts its application
especially in the eLearning process where more and more multimedia resources
are being used. While this can be seen as a problem, methods are available to
retrieve textual description and content from many types of media that can be
used to alleviate this issue.
Finally, as already mentioned, it appears obvious that the set of topics one
is mostly interested in learning about is a very subjective matter. We therefore
cannot expect for our method to ever be entirely accurate. Enabling interac-
tion with the constructed learning scopes and clusters seems therefore to be a
promising solution here. Indeed, we plan to integrate feedback from the user into
our approach, allowing them to mark certain clusters as “persistent” (i.e. they
should not disappear even if other clusters appear more important), irrelevant
(i.e. their activities should be either moved to other clusters or considered as
not interesting from the point of view of learning), merged (i.e. two learning
scopes might need to be combined) or as containing a different set of activities
(i.e. the user should be able to re-assign activities manually). The incremental
hierarchical clustering method described in this paper would therefore have to
be updated to be able to integrate those feedback.
10 Acknowledgment
This work has received funding from the European Union’s Horizon 2020 re-
search and innovation programme as part of the AFEL (Analytics for Everyday
Learning) project under grant agreement No 687916, and supported by the In-
sight Centre for Data Analytics, funded by Science Foundation Ireland.
References
1. Naif R Aljohani and Hugh C Davis. Learning analytics in mobile and ubiquitous
learning environments. 2012.
2. Patrick Carmichael and Katy Jordan. Semantic web technologies for education–
time for a turn to practice? Technology, Pedagogy and Education, 21(2):153–169,
2012.
3. Xin Chen, Mihaela Vorvoreanu, and Krishna Madhavan. Mining social media data
for understanding student’s learning experiences. IEEE Transactions on Learning
Technologies, 7(3):246–259, 2014.
4. Kathleen J Cotton. Monitoring student learning in the classroom. school improve-
ment research series close-up# 4. 1988.
5. Mathieu d’Aquin and Nicolas Jay. Interpreting data mining results with linked
data for learning analytics: motivation, case study and directions. In Proceedings
of the Third International Conference on Learning Analytics and Knowledge, pages
155–164. ACM, 2013.
Detection of Online Learning Activity Scopes 15
6. Mathieu dAquin, Alessandro Adamou, Stefan Dietze, Besnik Fetahu, Ujwal Gadi-
raju, Ilire Hasani-Mavriqi, Peter Holtz, Joachim Kimmerle, Dominik Kowald, Elis-
abeth Lex, et al. Afel: Towards measuring online activities contributions to self-
directed learning. In Proceedings of EC-TEL 2017 workshop ARTEL, 2017.
7. Rebecca Ferguson and Simon Buckingham Shum. Social learning analytics: five ap-
proaches. In Proceedings of the 2nd international conference on learning analytics
and knowledge, pages 23–33. ACM, 2012.
8. Giovanni Fulantelli, Davide Taibi, and Marco Arrigo. A semantic approach to
mobile learning analytics. In Proceedings of the First International Conference
on Technological Ecosystem for Enhancing Multiculturality, pages 287–292. ACM,
2013.
9. Danita Hartley and Antonija Mitrovic. Supporting learning by opening the student
model. In International Conference on Intelligent Tutoring Systems, pages 453–
462. Springer, 2002.
10. Denis Helic, Hermann Maurer, and Nick Scherbakov. Web based training: What
do we expect from the system. In Proceedings of ICCE, pages 1689–1694, 2000.
11. Riccardo Mazza and Vania Dimitrova. Coursevis: A graphical student monitoring
tool for supporting instructors in web-based distance courses. International Journal
of Human-Computer Studies, 65(2):125–139, 2007.
12. Riccardo Mazza and Christian Milani. Gismo: a graphical interactive student
monitoring tool for course management systems. In International Conference on
Technology Enhanced Learning, Milan, pages 1–8, 2004.
13. Colin McCormack and David Jones. Building a web-based education system. John
Wiley & Sons, Inc., 1997.
14. Fionn Murtagh. A survey of recent advances in hierarchical clustering algorithms.
The Computer Journal, 26(4):354–359, 1983.
15. A. Oeberst, J. Kimmerle, and U. Cress. What is knowledge? who creates it? who
possesses it? the need for novel answers to old questions. Mass collaboration and
education, 2016.
16. Lawrence C Ragan. Good teaching is good teaching. an emerging set of guiding
principles and practices for the design and development of distance education.
Cause/Effect, 22(1):20–24, 1999.
17. Felipe Barbosa Araújo Ramos, Anne Lorayne, Antonio Alexandre Moura Costa,
Reudismam Rolim de Sousa, Hyggo O Almeida, and Angelo Perkusich. Combining
smartphone and smartwatch sensor data in activity recognition approaches: an
experimental evaluation. In SEKE, pages 267–272, 2016.
18. Arnaud Ribert, Abdel Ennaji, and Yves Lecourtier. An incremental hierarchical
clustering. In Proceedings of the Vision Interface Conference, pages 586–591, 1999.
19. Christian Seeger, Alejandro Buchmann, and Kristof Van Laerhoven. myhealthas-
sistant: a phone-based body sensor network that captures the wearer’s exer-
cises throughout the day. In Proceedings of the 6th International Conference on
Body Area Networks, pages 1–7. ICST (Institute for Computer Sciences, Social-
Informatics and Telecommunications Engineering), 2011.
20. Diego Zapata-Rivera and Jim E Greer. Exploring various guidance mechanisms to
support interaction with inspectable learner models. In International Conference
on Intelligent Tutoring Systems, pages 442–452. Springer, 2002.