ArticlePDF Available

Abstract and Figures

The availability of personal digital devices in schools and at home are offering new ways of engaging students in the area of language learning. In this publication, we present a new approach on writing and blogging for children aged 8 to 12 years, which is especially helpful for those who struggle with the acquisition of German orthography. On a web-based platform the pupils can write essays and blog them later on. Combined with learning analytics methods we offer individualized feedback during the process of writing and a training database with appropriate exercises to support the students' autonomous learning.
Content may be subject to copyright.
Bulletin of the Technical Committee on Learning Technology (ISSN 2306-0212)
Abstract—The availability of personal digital devices in schools
and at home are offering new ways of engaging students in the
area of language learning. In this publication, we present a new
approach on writing and blogging for children aged 8 to 12 years,
which is especially helpful for those who struggle with the
acquisition of German orthography. On a web-based platform the
pupils can write essays and blog them later on. Combined with
learning analytics methods we offer individualized feedback
during the process of writing and a training database with
appropriate exercises to support the students’ autonomous
Index Terms—educational media, German spelling acquisition,
learning analytics, technology enhanced language learning
I. I
(LA) has gained more and more
recognition and importance since it was first mentioned in
the Horizon Report 2012 as a forthcoming trend [1]. Long and
Siemens also referred to Big Data and Analytics as the most
important influencing factors for the future of (high) school
education [2]. LA itself benefits from the ability to collect a
variety of different data from each user [3] in order to examine
the learning activity and the learning behavior more closely.
The combination of Technology Enhanced Language Learning
(TELL) with LA makes it possible to better understand the
language learning itself [4] and to automatically identify and
classify learners according to their skills and competences in
order to better support them [5] in language learning. In our
approach we strongly focus on TELL and LA in the field of
German orthography to provide students and teachers with
relevant data, which reflect the learning behavior of each
This research project is supported by the European Commission Erasmus+
program in the framework of the project IDeRBlog under grant
VG-SPS-SL-14-001616-3. For more information about the IDeRBlog-project
and its project partners from Germany: Gros, M., Adolph, H., Steinhauer, N.
(LPM Saarland); Biermeier, S., Ankner, L. (Albert-Weisgerber-Schule, St.
Ingbert); from Belgium: Huppertz, A., Cormann, M. (GS Raeren); from
Austria: Ebner, M., Taraghi, B., Ebner, M. (TU Graz); Gabriel, S., Wintschnig,
M. (KPH Wien/Krems); Aspalter, Ch., Martich, S., Ullmann, M. (PH Wien);
Edtstadler, K. (PH Steiermark), please visit our homepage:
(German language only).
Markus Ebner is with the department Educational Technology at Graz
University of Technology, 8010 Graz, Austria (corresponding author, phone:
+43 316 873 8567; e-mail:
Martin Ebner is head of Educational Technology department and senior
researcher at the Institute of Interactive Systems and Data Science at Graz
University of Technology, 8010 Graz, Austria (e-mail:
Konstanze Edtstadler is with the Institute of Professionalization in Early
Childhood and Primary Teacher Education at the University College of Teacher
Education Styria, 8010 Graz, Austria (email:
individual learner, thus enabling individualized and
personalized support [6] with appropriate exercises [7].
A. Overview
In this publication we want to present an ongoing research
work in the area of TELL and LA. Nowadays, the availability of
personal digital devices in the schools and classrooms offers
new ways of engaging students, also supported by the broad
availability of smartphones and tablets to use internet based
applications [8], [9]. This allows us to discover new ways of
learning for children in the research fields of mobile learning
(ML), LA and TELL. With the IDeRBlog project we try to
combine the acquisition of German orthography with text
writing, especially blogging, by the use of modern digital
instruments [10]. The current development is unique in the field
of literacy acquisition. Until now, fundamental requirements for
acquiring German orthography (cf. [10]) could only be fulfilled
by a highly professional face-to-face training. Especially giving
more specific feedback than to look up a word in a dictionary for
correcting misspelled words was only possible in an individual
setting. The current development facilitates the implementation
of an individual approach. So the main research question
addresses the idea, how to design an information system for
pupils, in order to assist them to improve their spelling ability
combined with writing (publishable) texts.
B. Background
Writing, besides reading and calculating, is one of the basic
skills pupils have to acquire in (elementary) school. It is
indispensable for the future participation in social life and
society. Especially, in the German speaking areas of Europe,
correct spelling is considered prestigious [11]. Therefore, it is of
great interest for teachers to identify shortcomings in the area of
orthography at an early stage in order to take appropriate
measures to eliminate them [12].
Our approach offers the pupils a web-based platform where
they can write short texts in form of blog entries. In contrast to
hand-written essays, these texts can be analyzed
semi-automatically. In the first step, feedback is provided for
correcting spelling mistakes. In contrast to an usual
auto-correction system these feedbacks do not simply offer the
correctly spelled words but strategy based hints for correcting
them in order to improve the child’s self-correction and
orthographic competence [10]. This is the unique feature of the
system as it takes in account several aspects of research in the
field of German orthography and its acquisition. The teachers
Why Will Technology Enhanced Language Learning be Essential for
Markus Ebner, Martin Ebner and Konstanze Edtstadler
Bulletin of the Technical Committee on Learning Technology (ISSN 2306-0212)
benefit from the initial evaluation of the text as it provides a
qualitative analysis of the spelling mistakes in order to gain
insight into the problematic orthographic areas of each pupil.
For this purpose, the misspelled words are categorized and
assigned to specific phenomena by the intelligent dictionary
[10], [13], [7].
This evaluation makes it possible for the teachers to take
appropriate measures for supporting each single child, such as
explanations and appropriate individual online exercises as well
as worksheets, which are also offered on the platform [10].
Furthermore, the progress of the child can be monitored over a
longer period of time and made available to the pupils, parents
and teachers. This makes it possible to address the child in a
more individual way. Subsequently, the analysis of the data
allows a better understanding of the spelling acquisition process
and allows new didactic approaches [14].
C. Approach
In order to set up the platform we had to fulfill different
criteria for our stakeholders: students (age 8 to 12 years),
teachers, parents and researchers.
First, we had to assure that the platform is easy and simple to
use. The presented feedback and the platforms design have to be
as simple as possible to avoid confusion and misinterpretation
between the various stakeholders [15], [16]. Therefore, we
included students from our partner schools as co-designers of
the platform, as suggested in NMC Horizon Report [17]. By the
aid of a graphic designer we drafted different color schemes and
mascots. With this approach we could assure to create a
graphically appealing and age appropriate website [18]. After
evaluation and rating by the students we developed the favored
design further and integrated it in our concept. Fig. 1 shows
scratch and final mascots from our website [14].
Second, we didn’t want to create a simple spell checker.
Therefore, in case of a spelling mistake, we provide hints to the
student for correcting the misspelled words (within the so-called
“intelligent dictionary”). This aims to encourage the pupils to
reflect about the language and become aware of the word
structure, which is important for acquiring the orthography [24].
The provided feedback is based on the theory of German
orthography and formulated in an understandable way for the
target group. As the feedback is strongly connected with the
qualitative analysis, its requirements were analyzed and
considered [13]. For constructing the intelligent dictionary
important words as well as frequently misspelled words and
their word forms are collected [10]. In a next step, their
corresponding misspelled word forms are "invented" depending
on the - previously defined - fine grained phenomena which are
subordinated to the coarse grained categories of the qualitative
analysis [10]. This means, that each misspelled word form, that
causes a specific feedback for correction, is connected with a
phenomenon - and subsequently with its category - that is
representing this type of mistake. The hierarchy of phenomenon
and category allows us to stay flexible and to add or delete
phenomena evidence-based on the long run. This systematic
approach will lead to a deeper and representative understanding
of the most problematic areas of German orthography.
Fig. 2 points out an example with hints to correct the
misspelled words. The text in English means: „Today we
discovered many new things in the woods. The distance
between our camp and the river was very far” [19]. The student
made two spelling mistakes: enddeckten (translated: (we)
discovered) with <*end> instead of <ent> and Endfernung
(translated: (the) distance) with <*End> instead of <Ent>,
which are shown to the student with the appropriate hints for
correction: “Think about the spelling of the world building
brick” [19].
Third, we wanted to provide a suitable training database with
exercises for students, teachers, and parents. Therefore, a pool
of around 260 online and offline exercises has been created for
different error categories [14]. The teachers get a more detailed
presentation of the challenging areas from the individual student
or the class with more detailed recommendations in
correspondence to the categories of the qualitative analysis of
the spelling mistakes.
Fig. 1. Figur
e creation: first scratches on the left and the final mascots from
the website on the right. The different mascots are offering different function
for the students (from left to right): writing, exercising, reading [14].
Fig. 2. Example of a text correction [19].
Bulletin of the Technical Committee on Learning Technology (ISSN 2306-0212)
Fig. 3 shows the feedback overview from the perspective of a
student. The top 5 error categories are listed and
recommendations for exercises (on- or offline) are offered.
Additionally, the student should take the interactive spelling
courses consistent with the spelling problems, which offer an
explanation and are also offered for free on the platform.
Fourth, we had to assure that the students will use the
platform frequently. Therefore, we decided to include a blog
system in it to “provide relevant reasons and audiences for
writing” [20]. Compared to a typical essay writing in a
classroom, it can be expected that the motivation to formulate
and revise a text many times is higher with the opportunity of
publishing it in a blog [10].
Fig. 4 shows the general workflow on the platform for
teachers and students. A pupil writes the text in the provided
writing area (1). After the orthographic analysis of the submitted
text, conducted by the intelligent dictionary (2), proper
feedback is provided to the student. Now the student can further
correct the text as often as needed (3) or submit the text (4). This
intermediate step ensures that the student can correct spelling
mistakes independent and self-reflexive [21]. After submission
the teacher gets a notification (5) for reviewing the text. The
teacher now has the possibility to correct and/or add additional
feedback (6) to the text. A report is generated and sent back to
the pupil (7). The student’s parents are also able to access the
platform in order to supervise the progress and the suggested
exercises. The teacher can instruct the student to redo the essay
and send it back to her/him with additional hints and comments
beyond orthography (7a). The student can choose to blog the
essay in the provided blogs (8). Recommendations for training
exercises are provided by the system to the student (9) and the
teacher for the student and class (10). [7]
This paper presents a new approach on TELL assisted by LA
techniques for identifying orthographic areas of interest to work
on and the overall progress of the student. A unique feature of
this platform is the automatic feedback for the students during
text creation, provided by our intelligent dictionary [10], [7].
Fig. 3. Individual feedback view with recommendations for training database
exercises for students and parents.
Fig. 4. General workflow for teachers and students [7].
Bulletin of the Technical Committee on Learning Technology (ISSN 2306-0212)
The qualitative analysis for teachers supports the selection for
proper exercises for the class. Further, the training database
provides recommended exercises for teacher-centered and
learner-centered learning. In-depth analysis [22] will be
conducted to understand the process of spelling acquisition in
more detail. The analysis of systematically made mistakes for
teachers allows the measurement of the student’s individual or
class performance, in the long run [23].
It can be summarized that our approach consists of the
possibility for pupils to provide a web platform, where they can
compose and publish short essays, which are checked against
the intelligent dictionary to point out failures in real time. In the
background misspellings are tracked and result in an overview
diagram to display systematically wrong written words ordered
by orthographic categories. This should help pupils to enhance
their writing skills through technology in a meaningful manner.
As this is the first development in the field of LA and German
orthography the currently existing intelligent dictionary can be
labeled as a prototype, which works well and has the power to
be developed further, especially by integrating much more
words and its corresponding mistakes. Feedback and
experiences from schools gathered so far show reveal high
acceptability. For example, 149 students of our partner schools
(grade 3 to 6) submitted between October 2016 and January a
total of 429 texts. [7].
The authors would like to thank all teachers of our partner
schools and 3rd-party schools as well as our partners for their
commitment to the project and the provided feedback. For more
information about the IDeRBlog project please visit our
homepage: (German language only).
[1] L. Johnson, S. Adams and M. Cummins (2012). The NMC Horizon
Report: 2012 Higher Education Edition. Austin, Texas: The New Media
Consortium. (last
accessed: March 2017)
[2] P. Long and G. Siemens (2011). Penetrating the Fog: Analytics in
Learning and Education. In: EDUCAUSE Review Magazine. Volume 46.
5, p. 31-40
[3] M. Khalil and M. Ebner (2015). Learning Analytics: Principles and
Constraints. In: Proceedings of World Conference on Educational
Multimedia, Hypermedia and Telecommunications 2015. Chesapeake,
VA: AACE, p. 1326-1336.
[4] A. Bader-Natal and T. Lotze (2011). Evolving a learning analytics
platform. In: 1st International Conference on Learning Analytics and
Knowledge 2011, The Technology Enhanced Knowledge Research
Institute, Athabasca University, Canada. 1, 4, 5
[5] B. Taraghi, A. Saranti, M. Ebner, V. Müller and A. Großmann (2015).
Towards a Learning-Aware Application Guided by Hierarchical
Classification of Learner Profiles. In: Journal of Universal Computer
Science (J.UCS), vol. 21, no. 1 (2015), p. 93-109
[6] M. Ebner and M. Schön (2013). Why Learning Analytics for Primary
Education Matters!, In: Karagiannidis, C./Graf, S (Hrsg.): Bulletin of the
Technical Committee on Learning Technology, Volume 15(2), p. 14-17
[7] M. Ebner, K. Edtstadler and M. Ebner (2017). Tutoring Writing and
Spelling Skills within a Web-based Platform for Children. Universal
access in the information society: international journal. Springer, p. 1-19,
[8] M. Ebner, W. Nagler and M. Schön (2012). Have They Changed? Five
Years of Survey on Academic Net-Generation. In Proceedings of World
Conference on Educational Multimedia, Hypermedia and
Telecommunications 2012 (pp. 343-353). Chesapeake, VA: AACE
[9] M. Grimus and M. Ebner (2016). Mobile Phones and Learning -
Perceptions of Austrian Students aged from 11 to 14 Years. In:
Proceedings of EdMedia: World Conference on Educational Media and
Technology 2016. Association for the Advancement of Computing in
Education (AACE). pp. 106-115.
[10] K. Edtstadler, M. Ebner and M. Ebner (2015). Improved German Spelling
Acquisition through Learning Analytics. In: eLearning Papers 45, pp.
[11] H. Küttel (2007). Probleme des Erwerbs der Orthographie. In Nerius, D.
(Ed.) Deutsche Orthographie. Georg Olms, pp. 417-451
[12] M. Ebner, B. Taraghi, M. Ebner, C. Aspalter, S. Biermeier, K. Edtstadler,
S. Gabriel, G. Goor, M. Gros, A. Huppertz, S. Martich, N. Steinhauer, M.
Ullmann and K. Ziegler (2015). Design für eine Plattform zum
Schreibenlernen im Grundschulalter. In: Proceedings of DeLFI
Workshops 2015 co-located with 13th e-Learning Conference of the
German Computer Society (DeLFI 2015), p. 118-122
[13] K. Edtstadler (2015). Qualitative Fehleranalyse im Schriftspracherwerb.
Kritik und Kriterien. In: Lindner D., Gabriel S. & Beer R. (Eds.) Dialog
Forschung – Tag der Forschung 2015, Lit-Verlag.
[14] M. Ebner, M. Ebner and K. Edtstadler (2016). Learning Analytics and
Spelling Acquisition in German - a first prototype. In Z. Panayiotis & A.
Ioannou (eds), Learning and Collaboration Technologies: Third
International Conference, LCT 2016, Held as Part of HCI Inter-national
2016. Springer International, Toronto, ON, Canada, pp. 405-416. DOI:
[15] R. S. J. D. Baker, E. Duval, J. Stamper, D. Wiley and S. Buckingham
Shum (2012). Panel: educational data mining meets learning analytics.
In: Buckingham Shum, S., Gasevic, D. & Ferguson, R. (Eds.)
Proceedings of 2nd International Conference on Learning Analytics &
Knowledge (LAK’12), New York, USA, 20
[16] B. Neuhold (2013). Learning Analytics-Mathematik Lernen neu gedacht,
BoD–Books on Demand.
[17] L. Johnson, S. Adams Becker, V. Estrada, A. Freeman, P. Kampylis, R.
Vuorikari and Y. Punie (2014). Horizon Report Europe: 2014 Schools
Edition. Luxembourg: Publications Office of the European Union, &
Austin, Texas: The New Media Consortium
[18] J. Liebal and M. Exner (2011). Usability für Kinds. Springer Fachmedien
Wiesbaden, Wiesbaden.
[19] Ebner, M., Edtstadler, K., & Ebner, M. (2017, July). Learning Analytics
and Spelling Acquisition in German–Proof of Concept. In International
Conference on Learning and Collaboration Technologies (pp. 257-268).
Springer, Cham.
[20] Government of South Australia. Department for Education and Child
Development, issuing body (2011). Spelling: from beginnings to
proficiency: a spelling resource for planning, teaching, assessing and
reporting on progress, Adelaide, South Australia, Department for
Education and Child Development
[21] H. Bartnitzky (2010). Individuell fördern–Kompetenzen stärken.
Grundschule aktuell (9), pp. 6-11
[22] G. Siemens (2012). Learning analytics: envisioning a research discipline
and a domain of practice. In Proceedings of the 2nd International
Conference on Learning Analytics and Knowledge, ACM, pp. 4-8
[23] M. Schön, M. Ebner and G. Kothmeier (2012). It's just about learning the
multiplication table. In Proceedings of the 2nd International Conference
on Learning Analytics and Knowledge, ACM, pp. 73-81
[24] A. Müller. (2010). Rechtschreiben lernen. Die Schriftstruktur entdecken -
Grundlagen und Übungsvorschläge. Seelze: Klett & Kallmeyer
ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
German orthography is known to be quite difficult to master, especially for primary-school pupils in writing texts [cf. 1]. In order to support children with the acquisition of German orthography, we are developing a web-based platform for German-speaking users based on learning analytics techniques. Our goal is to motivate pupils age 8 to 12 to improve their spelling abilities by writing texts and by the possibility to publish them. Concerning spelling in combination with learning analytics the system provides - in case of an orthographic mistake - a specific feedback that encourages pupils to think about the spelling and to correct it. Based on occurred mistakes the teachers and the students are provided with a qualitative analysis of the mistakes. This analysis shows the problematic orthographic areas and gives suggestions for online and offline exercises as well as online courses that are explaining the orthographic phenomena. The aim of this article is to describe the architecture of the web-based system and a proof of concept by evaluating 60 essays. Furthermore, relevant background information is given in order to gain a better understanding in the complex interdisciplinary development.
Conference Paper
Full-text available
This article aims to report on the findings of a study of perception for using mobile phones for learning in Austria. Surveys were conducted to examine the ownership and usage of mobile phones of eight to 14 year old pupils. Findings indicate that gathered data show a lack of perceptions for benefits of mobile phones for learning. Issues based on the research in 2013 and 2014 are discussed with regard to demands and challenges for education. Using their own mobile phones for various learning activities could build a bridge between students' practice in everyday life and school learning, and developing indispensable 21 st century skills.
Conference Paper
Full-text available
Data-driven learning in combination with emerging academic areas such as Learning Analytics (LA) has the potential to tailor students’ education to their needs [1]. The aim of this article is to present a web-based training platform for primary school pupils who struggle with the acquisition of German orthography. Our objective is the improvement in their writing and spelling competences. The focus of this article is on the development of the platform and the details concerning the requirements and the design of the User Interface (UI). In combination with Learning Analytics, the platform is expected to provide deeper insight into the process of spelling acquisition. Furthermore, aspects of Learning Analytics will help to develop the platform, to improve the exercises and to provide better materials in the long run.
Conference Paper
Full-text available
Within the evolution of technology in education, Learning Analytics has reserved its position as a robust technological field that promises to empower instructors and learners in different educational fields. The 2014 horizon report (Johnson et al., 2014), expects it to be adopted by educational institutions in the near future. However, the processes and phases as well as constraints are still not deeply debated. In this research study, the authors talk about the essence, objectives and methodologies of Learning Analytics and propose a first prototype life cycle that describes its entire process. Furthermore, the authors raise substantial questions related to challenges such as security, policy and ethics issues that limit the beneficial appliances of Learning Analytics processes.
Full-text available
Learner profiling is a methodology that draws a parallel from user profiling. Implicit feedback is often used in recommender systems to create and adapt user profiles. In this work the implicit feedback is based on the learner's answering behaviour in the Android application UnlockYourBrain, which poses different basic mathematical questions to the learners. We introduce an analytical approach to model the learners' profile according to the learner's answering behaviour. Furthermore, similar learner's profiles are grouped together to construct a learning behaviour cluster. The choice of hierarchical clustering as a means of classification of learners' profiles derives from the observations of learners behaviour. This in turn reflects the similarities and subtle differences of learner behaviour, which are further analysed in more detail. Building awareness about the learner's behaviour is the first and necessary step for future learning-aware applications.
Full-text available
Nell’era di Internet, delle tecnologie mobili e dell’istruzione aperta, la necessità di interventi per migliorare l’efficienza e la qualità dell’istruzione superiore è diventata pressante. I big data e il Learning Analytics possono contribuire a condurre questi interventi, e a ridisegnare il futuro dell’istruzione superiore. Basare le decisioni su dati e sulle evidenze empiriche sembra incredibilmente ovvio. Tuttavia, l’istruzione superiore, un campo che raccoglie una quantità enorme di dati sui propri “clienti”, è stata tradizionalmente inefficiente nell’utilizzo dei dati, spesso operando con notevole ritardo nell’analizzarli, pur essendo questi immediatamente disponibili. In questo articolo, viene evidenziato il valore delle tecniche di analisi dei dati per l’istruzione superiore, e presentato un modello di sviluppo per i dati legati all’apprendimento. Ovviamente, l’apprendimento è un fenomeno complesso, e la sua descrizione attraverso strumenti di analisi non è semplice; pertanto, l’articolo presenta anche le principali problematiche etiche e pedagogiche connesse all’utilizzo delle tecniche di analisi dei dati in ambito educativo. Cionondimeno, il Learning Analytics può penetrare la nebbia di incertezza che avvolge il futuro dell’istruzione superiore, e rendere più evidente come allocare le risorse, come sviluppare vantaggi competitivi e, soprattutto, come migliorare la qualità e il valore dell’esperienza di apprendimento.
Full-text available
The ubiquitous availability of applications enables us to offer students opportunities to test and train competences in almost every situation. At Graz University of Technolgy two apps for testing competences in multiplication are developed. They estimate the competence level of every user and adapt to their individual development in this domain. They collect a lot of data during a longer period, which could be used on further research. In the foreground they give feedback in a compact and clearly arranged way to the single student and the teachers of classes. But furthermore the analysis of the data during a longer term showed us, that the process of testing and giving feedback has also an positive effect on learning. We emphasize that this quality in supporting the students could not be achieved by human teachers. Information Technology and Learning Analytics gives them a wider radius to perceive specific behavior and establishes their capacity for storing and processing all the relevant data.
Conference Paper
Full-text available
One of the first and basic mathematical knowledge of school children is the multiplication table. At the age of 8 to 10 each child has to learn by training step by step, or more scientifically, by using a behavioristic learning concept. Due to this fact it can be mentioned that we know very well about the pedagogical approach, but on the other side there is rather less knowledge about the increase of step-by-step knowledge of the school children. In this publication we present some data documenting the fluctuation in the process of acquiring the multiplication tables. We report the development of an algorithm which is able to adapt the given tasks out of a given pool to unknown pupils. For this purpose a web-based application for learning the multiplication table was developed and then tested by children. Afterwards so-called learning curves of each child were drawn and analyzed by the research team as well as teachers carrying out interesting outcomes. Learning itself is maybe not as predictable as we know from pedagogical experiences, it is a very individualized process of the learners themselves. It can be summarized that the algorithm itself as well as the learning curves are very useful for studying the learning success. Therefore it can be concluded that learning analytics will become an important step for teachers and learners of tomorrow.
Conference Paper
Full-text available
Web-based learning systems offer researchers the ability to collect and analyze fine-grained educational data on the performance and activity of students, as a basis for better understanding and supporting learning among those students. The availability of this data enables stakeholders to pose a variety of interesting questions, often specifically focused on some subset of students. As a system matures, the number of stakeholders, the number of interesting questions, and the number of relevant sub-populations of students also grow, adding complexity to the data analysis task. In this work, we describe an internal analytics system designed and developed to address this challenge, adding flexibility and scalability. Here we present several examples of typical examples of analysis, discuss a few uncommon but powerful use-cases, and share lessons learned from the first two years of iteratively developing the platform.