ChapterPDF Available

Mining and Visualizing Trends from Educational Systems using Linked Data

Authors:

Abstract and Figures

This work introduces a case study on usage of semantic context modelling and creation of Linked Data from logs in educational systems like a Personal Learning Environment (PLE) with purpose on improvements in generally with respect to social and semantic analysis of the parameters on user and activity centric level [3]. Sample case study demonstrates the usage of semantic modelling of the activity context using adequate domain specific ontologies and semantic technologies and visualization of such data as result of analysis of such modelled data represented in the form of Linked Data. This approach implies the easy interfacing and extensibility on machine or human level offering fast insight on statistical trends.
Content may be subject to copyright.
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 164
Mining and Visualizing Trends from Educational
Systems using Linked Data
Authors: S. Softic1,*, B. Taraghi1, M. Ebner1
Affiliations:
1 Graz University of Technology
*Correspondence to: selver.softic@tugraz.at
Abstract: This work introduces a case study on usage of semantic context modelling and
creation of Linked Data from logs in educational systems like a Personal Learning Environment
(PLE) with purpose on improvements in generally with respect to social and semantic analysis of
the parameters on user and activity centric level [3]. Sample case study demonstrates the usage
of semantic modelling of the activity context using adequate domain specific ontologies and
semantic technologies and visualization of such data as result of analysis of such modelled data
represented in the form of Linked Data. This approach implies the easy interfacing and
extensibility on machine or human level offering fast insight on statistical trends.
One Sentence Summary: This work introduces a case study on usage of semantic context
modelling and creation of Linked Data for mining trends from logs in educational systems.
1. Introduction
Modern learning environments, besides learning resources provided by the educational
institution, aim at integration of popular internet services that might be of interest of learners
like: Google Hangout, Facebook, YouTube, Newsgroups, Twitter, Slideshare just to name some
of them. Maintaining such platforms is intensively changing process demanding from
maintainers to actively adapt their systems to the learner needs. Nowadays, learners are
expecting focused and simple platforms helping them to organize their learning process.
Learners don’t want to waste their time on information and actions which could disturb or
prolong their learning. Therefore user adaptively is a strong impact on acceptance of such
platforms and should be matter of continuous improvement.
Cumulated system monitoring data (e.g. logs) of such environments offers new opportunities for
optimization [8]. Such data can contribute the better personalization and adaptation of the
learning process but also improve the design of learning interfaces.
Main contribution of the paper is a case study done with the logs from PLE at Graz University of
Technology presenting approach using Linked Data to mine the usage trends from PLE. The idea
behind this effort is aiming at gaining insights useful for optimization of PLE [4], and adapting
Draft - extended version originally published in: Softic, S., Taraghi, B., Ebner, M. (2015) Mining and
Viszualising Trends from Educational Systems using Linked Data. In: Immersive Education. Ebner, M., Erenli,
K., Malaka, R., Pirker, J., Walsh, A. (Eds.). Communications in Computer and Information Science 486.
Springer. pp. 17-26
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 165
them to the learners, by using more personalization, e.g. through recommendation of interesting
learning widgets.
2. Related Work
This section report shortly about most relevant related work regarding PLE (at Graz University
of Technology), and semantic technologies used in this work.
2.1 PLE at Graz University of Technology
The main idea of PLE at Graz University of Technology (http://ple.tugraz.at) is to integrate
existing university services, and resources [2], with services and resources from the World Wide
Web in one platform and in a personalized way [2]. The TU Graz PLE contains widgets [14 - 16]
that represent the resources and services integrated from the World Wide Web. Web today
provides lots of different services; each can be used as supplement for teaching and learning. The
PLE has been redesigned in 2011, using metaphors such as apps and spaces for a better learner-
centered application and higher attractiveness [1, 13]. In order to enhance PLE in general and
improve the usability as well as usefulness of each individual widget a tracking module was
implemented by prior work [17]. Different works outlined the importance of tracking activity
data in Learning Management Systems [9, 18]. None of them addressed the issue of intelligently
structuring monitoring data in context and processing it to provide a flexible interface that
ensures maximum benefit from collected information.
2.2 Semantic Modeling of Activities in PLE
The Semantic Web standards like RDF (http://www.w3.org/RDF) and SPARQL
(http://www.w3.org/TR/rdf-sparql-query/) enable data to be and for interchange and queried as
graphs. Data schema is usually projected on specific knowledge domain using adequate
ontologies. This approach has been fairly successful used to generate correct interpretation of
web tables [5] to advance the learning process [7, 3] as well to support the controlled knowledge
generation in E-learning environments [12]. This potential was also recognized by resent
research in IntelLEO Project (http://intelleo.eu). IntelLEO delivered an ontology framework
where Activities Ontology (http://www.intelleo.eu/ontologies/activities/spec/) is used to model
learning activities and events related to them. Due to the relatedness to the problem that is
addressed by this work these ontologies have been used to model the context of analytic data
collected from PLE logs.
3. Approach for Mining Usage Logs
Presented approach is based on transforming collected data from PLE logs into instances of
Activities Ontology. This process produces as output Linked Data graphs query able by
SPARQL standard query language. The SPARQL is applied to query the Linked Data and mine
the output for analytic visualizations (see Figure 1). The overall goal of this process is
summarization, visualizations and evaluation of statistic data that enable the PLE optimization,
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 166
in interface design and adaptation of content of PLE to the learner. This approach is inspired by
the examples from current research in the area of Self-regulated Learners (SRL) [3, 11].
Figure 1. Mining pipe line for PLE usage logs.
3.1 Dataset
Data used in the case study originates from Personal Learning Environment (PLE)
(https://ple.tugraz.at) developed for the needs of Graz University of Technology which serves
currently more than 4000 users. The data was collected during two years period in order to
generate analytics reports with visualization support for overall usage and process view on our
environment following the research trends of previous years [10, 6].
3.2 Modeling Usage Logs
The main precondition for meaningful mining of usage trends is choice of appropriate data
model since RDF offers only the framework how structure and link data. This task concerns
mostly the choice of the right vocabulary or ontology. Activities Ontology offers a vocabulary to
represent different activities and events related to them inside of a learning environment with
possibility to describe and reference the environment (in this case PLE) where these activities
occur. Formulation (in Figure 2.) depicts an instance of usage ao:Logging instance. This excerpt
comes from the tracking module. Such data is stored in a memory RDF Store (Graph Database
for Linked Data) with SPARQL Endpoint (interface where Linked Data can be queried).This
sample instance reflects that a usage ao:Logging event occurred at certain time point inside the
learning widget named LatexFormulaToPngWidget as ao:Enviroment. As shown in this
example vocabularies and ontologies which suit well to specific case enriches the analytic
process, in a very compact manner, with a high level of expressiveness.
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 167
Figure 2. Sample model of a usage log in N3 notation.
3.3 Querying of Usage Logs
Usage logs data presented as Linked Data graph are query able using SPARQL. In this way we
are able to answer the questions like "Show me the top 15 used widgets?". Figure 3. represents
exactly this question stated in the manner of SPARQL syntax.
Figure 3. Querying the intensity of usage of top 15 widgets in PLE.
4. Preliminary Results, Conclusion and Outlook
As preliminary result presented approach allows mining the trends of PLE widgets usage overall
time periods like presented in Figure 4. This violin graph depicts the visual answer of the query
from Figure 3. Also the intensity shows that as expected that most activity on widgets happens at
the beginning when PLE is presented in introductory lectures to the newcomers and freshmen
and at the end of academic terms when most of the students prepare for examinations.
Advantages of Linked Data approach is usage of standardized web technologies which are
scalable and flexible regarding the changes of representation structure of data.
SPARQL as query language which operates over the Linked Data graphs of usage logs offers
much flexibility regarding the generation of results that should be visualized in end instance. It
also allows on-demand statistical accumulations that can be used in the future as basic stats for
recommendation of new widgets in the PLE or similar tasks.
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 168
Figure 4. Visualizing the usage widget wise for top 15 widgets for year 2012.
References and Notes:
1. Ebner, M., Scerbakov, N., Taraghi, B., Nagler, W., Kamrat, I.: Teaching and learning in
higher education - an integral approach. Society for Information Technology and Teacher
Education International Conference pp. 428-436 (2010)
2. Ebner, M., Taraghi, B.: Personal learning environment for higher education-a First prototype.
Proceedings of World Conference on Educational Multimedia, Hypermedia and
Telecommunications pp. 1158-1166 (2010)
3. Jeremic, Z., Jovanovic, J., Galiasevic, D.: Personal learning environments on the social
semantic web. Semantic Web (2012)
4. Mazza, R., Milani, C.: Exploring usage analysis in learning systems: Gaining insights from
visualisations. In: Workshop on Usage Analysis in Learning Systems, Proceedings of
Artificial Intelligence in Education. Amsterdam (2005)
5. Mulwad, V., Finin, T., Syed, Z., Joshi, A.: Using linked data to interpret tables. In: Hartig,
O., Harth, A., Sequeda, J. (eds.) COLD. CEUR Workshop Proceedings, vol. 665. CEUR-
WS.org (2010), http://dblp.uni-trier.de/db/conf/semweb/cold2010.html#MulwadFSJ10a
6. Pardo, A., Kloos, C.D.: Stepping out of the box: towards analytics outside the learning
management system. In: Proceedings of the 1st International Conference on Learning
Analytics and Knowledge. pp. 163-167. LAK '11, ACM, New York, NY, USA (2011),
http://doi.acm.org/10.1145/2090116.2090142
7. Prinsloo, P., Slade, S., Galpin, F.: Learning analytics: challenges, paradoxes and
opportunities for mega open distance learning institutions. In: Proceedings of the 2nd
E-iED 2014 ImmersiveEducation.org
PROCEEDINGS 169
International Conference on Learning Analytics and Knowledge. pp. 130-133. LAK '12,
ACM, New York, NY, USA (2012), http://doi.acm.org/10.1145/2330601.2330635
8. Rosen, D., Miagkikh, V., Suthers, D.: Social and semantic network analysis of chat logs. In:
Proceedings of the 1st International Conference on Learning Analytics and Knowledge. pp.
134-139. LAK '11, ACM, New York, NY, USA (2011),
http://doi.acm.org/10.1145/2090116.2090137
9. Santos, J.L., Govaerts, S., Verbert, K., Duval, E.: Goal-oriented visualizations of activity
tracking: a case study with engineering students. In: Proceedings of the 2nd International
Conference on Learning Analytics and Knowledge. pp. 143-152. LAK'12, ACM, New York,
NY, USA (2012), http://doi.acm.org/10.1145/2330601.2330639
10. Santos Odriozola, J.L., Verbert, K., Govaerts, S., Duval, E.: Visualizing PLE usage. In:
Proceedings of EFEPLE11 1st Workshop on Exploring the Fitness and Evolvability of
Personal Learning Environments,. pp. 34-38. CEUR WS (Aug 2011),
https://lirias.kuleuven.be/handle/123456789/322006
11. Siadaty, M., Jovanovic, J., Pata, K., Holocher-Ertl, T., Gasevic, D., Milikic, N.: A semantic
web-enabled tool for self-regulated learning in the workplace. In: ICALT. pp. 66-70. IEEE
Computer Society (2011), http://dblp.uni-
trier.de/db/conf/icalt/icalt2011.html#SiadatyJPHGM11
12. Softic, S., Taraghi, B., Halb, W.: Weaving social e-learning platforms into the web of linked
data. Proceedings of I-SEMANTICS pp. 559-567 (2009)
13. Taraghi, B., Ebner, M., Clemens, K.: Personal learning environment – generation 2.0 pp.
1828-1835 (2012)
14. Taraghi, B., Ebner, M., Schaffert, S.: Personal learning environments for higher education: A
mashup based widget concept. Proceedings of the Second International Workshop on
Mashup Personal Learning Environments (MUPPLE 2009), Nice, France (2009)
15. Taraghi, B., Ebner, M., Till, G., Mühlburger, H.: Personal learning environment - a
conceptual study. International Conference on Interactive Computer Aided Learning pp. 25-
30 (2009)
16. Taraghi, B., Mühlburger, H., Ebner, M., Nagler, W.: Will personal learning environments
become ubiquitous through the use of widgets? Proceedings of I-KNOW, 329-335 (2009)
17. Taraghi, B., Stickel, C., Ebner, M.: Survival of the fittest - utilization of natural selection
mechanisms for improving ple. Proceedings of the first Workshop on Exploring the Fitness
and Evolvability of Personal Learning Environments pp. 4-9 (2011)
18. Verbert, K., Drachsler, H., Manouselis, N., Wolpers, M., Vuorikari, R., Duval, E.: Dataset-
driven research for improving recommender systems for learning. In: Proceedings of the 1st
International Conference on Learning Analytics and Knowledge. pp. 44-53. LAK '11, ACM,
New York, NY, USA (2011), http://doi.acm.org/10.1145/2090116.2090122
ResearchGate has not been able to resolve any citations for this publication.
Full-text available
Conference Paper
Despite all the research on student retention and success since the first conceptual mappings of student success e.g. Spady [12], there have not been equal impacts on the rates of both student success and retention. To realise the potential of learning analytics to impact on student retention and success, mega open distance learning (ODL) institutions face a number of challenges, paradoxes and opportunities. For the purpose of this paper we critique a 'closed' view of learning analytics as focusing only on data produced by students' interactions with institutions of higher learning. Students are not the only actors in their learning journeys and it would seem crucial that learning analytics also includes the impacts of all stakeholders on students' learning journeys in order to increase the success of students' learning. As such the notion of 'Thirdspace' as used by cultural, postmodern and identity theorists provide a useful heuristic to map the challenges and opportunities, but also the paradoxes of learning analytics and its potential impact on student success and retention. This paper explores some of these challenges, paradoxes and opportunities with reference to two mega ODL institutions namely the Open University in the UK (OU) and the University of South Africa (Unisa). Although these two institutions share a number of characteristics, there are also some major and important differences between them. We explore some of the shared challenges, paradoxes and opportunities learning analytics offer in the context of these two institutions.
Full-text available
Article
In the current ongoing work we propose the use of tracking and feedback mechanisms in order to improve our Personal Learning Environment (PLE), officially launched in October 2010. The approach can be seen as a necessary prerequisite similar to the darwinistic model of evolution. This means the implemented widgets will be improved (variation) and removed (selection) according to the observations. This paper will describe the backgrounds, methods and some details of the technical implementation.
Full-text available
Conference Paper
Teaching and Learning efforts at universities has been dominated by Learning Management Systems since years now. On the other side the so-called Web 2.0 technologies arise and assist teachers as well as learners through communication or collaborating with each other. Furthermore new web technologies like mashups or new devices like mobile phones allow us to work with the World Web Web from anywhere at anytime. In this publication a so-called Personal Learning Environment is introduced which was launched at Graz University of Technology for the first time in 2010. After a prototype phase a complete redesign were carried out to address more appropriate to users' needs. With the help of metaphors like spaces and apps the interface became quite easily and fulfilled the change towards learner-centered framework. It can be concluded that the learning environment of tomorrow has to integrate Web services as well as university wide services in an easy and understandable way to become a Personal Learning Environment.
Full-text available
Conference Paper
In the current ongoing work we propose the use of tracking and feedback mechanisms in order to improve our Personal Learning Environment (PLE), officially launched in October 2010. The approach can be seen as a necessary prerequisite similar to the darwinistic model of evolution. This means the implemented widgets will be improved (variation) and removed (selection) according to the observations. This paper will describe the backgrounds, methods and some details of the technical implementation.
Full-text available
Conference Paper
This paper presents the IT-environment of Graz University of Technology for supporting learning and teaching processes. Bearing in mind that future education strongly bases on technology the focus of tomorrow will not be on the development of one big platform – it will be to build an appropriate environment to connect different services. The concept of TU Graz is the combination of mainly three big platforms – an administrative system (TUGRAZonline, a learning management system (TU Graz TeachCenter) and a blogosphere (TU Graz LearnLand). Due to the fact that teachers and learners need also a kind of monitoring, especially if the WorldWideWeb is an integrated part of the learning environment, the development of a Personal Learning Environment (PLE) becomes indispensable. The paper describes the concept in detail as well as the used systems and points out the advantages of that IT-environment for the present as well as for the future.
Full-text available
Conference Paper
It is obvious that in the future the World Wide Web as a whole together with the many distributed online applications, tools and services play a very significant role in Technology Enhanced Learning. The integration of all these possibilities on the web in a Personal Learning Environment (PLE) in a way that the learners can select, individualize and customize the learning resources and services according to their needs and interests can support learners and teachers and enhance learning in general. For this purpose Graz University of Technology has developed a PLE that bases on mashup of widgets. In this paper the PLE architecture in general is described. The widget-based approach that follows the W3C standard is pointed out and the first widget prototypes as well as some student projects for widget development are illustrated.
Full-text available
Conference Paper
Due to the enormous growth of distributed applications, services, tools and resources, it is not easy for end users to come across existing services, manage and use them in a matter which is customized according to their personal needs. Mashups can be a very interesting approach to overcome challenges of distributed (unknown) services. Using mashups in a Personal Learning Environment (PLE) can help to connect resources and applications in one environment customized to the needs of individual users. In this paper a first approach and the concept of a PLE especially for higher education is described. The technological concept is introduced and design issues are pointed out as well as the first prototype is described.
Full-text available
Article
Nowadays Personal Learning Environments (PLEs) are described as the use of different social software tools for learning and teaching. The use of common web browsers often is a precondition to fulfil the requirements of social software tools. In this publication a new perspective as well as a couple of prototypes is presented to allow a more independent solution in this context. Using the new JavaFX technology so called widgets are implemented which can be used on different devices as well as different operating systems. Furthermore also the web browser can be replaced by a browser instance. It can be summarized that through the use of widgets the learning environment of the future can be more individualized and personalized.
Conference Paper
Increasing motivation of students and helping them to reflect on their learning processes is an important driver for learning analytics research. This paper presents our research on the development of a dashboard that enables self-reflection on activities and comparison with peers. We describe evaluation results of four iterations of a design based research methodology that assess the usability, use and usefulness of different visualizations. Lessons learned from the different evaluations performed during each iteration are described. In addition, these evaluations illustrate that the dashboard is a useful tool for students. However, further research is needed to assess the impact on the learning process.
Article
See https://lirias.kuleuven.be/handle/123456789/322006