Rationale

In the last two years, Learning Analytics is undoubtedly among the most trending topics in Education. Since there is currently not one, but multiple approaches to the topic –and even definitions of Learning Analytics– the range of different studies, experiences, tools and applications for Learning Analytics is growing at an overwhelming pace. There are some outstanding examples of these tools, from institution-supported modules –e.g. Moodle, Blackboard, the Khan Academy– to ad-hoc developments –e.g. Ruipérez-Valiente et al. (2013), Dimopoulos et al. (2013), Gilfus Analytics (2014). Furthermore, this variety is also present in the methods and tools used in Educational Data Mining (Romero and Ventura, 2007; 2010) and applications used for educational data visualization –e.g. Gómez-Aguilar et al. (2013).

But despite the many studies which have been carried out using this methods and tools, determining which is more appropriate to perform Learning Analytics. Of course, the answer to that question is extremely complex and subjective, as the suitability of one or another technique relies greatly on the kind of context, purpose and objectives of the analysis. Moreover, it is obvious that the same problem may be present in different contexts allowing for different solutions.

Also, the nature and amount of data may greatly affect the suitability, and even the validity, of a technique or tool when applied to Learning Analytics. Regarding the nature of data, it is necessary to initially define the selection criteria to determine which of the different data available are relevant for analysis (Duval and Verbert, 2012) for a specific context –as Long and Siemens (2012) put it: “using analytics requires that we think carefully about what we need to know and what data is most likely to tell us what we need to know”. With regards to the amount of data, there is scant research on the minimum –or even maximum– number of records necessary to effectively use the different techniques and tools for Learning Analytics in the different educational contexts that may occur.

This track is then conceived as a facilitator to share experiences with the creation and application of tools for learning analytics, so that: 1) a comprehensive view is offered on the different solutions provided by Learning Analytics and which problems they are solving; 2) synergies may emerge from the contributions and view of the participants on the track, and be directed towards the achievement of common goals; and 3) directions on the future developments for Learning Analytics may be pointed out, in particular their use in the context of courses with large enrolments such as MOOCs.

This track is then conceived as a facilitator to share experiences with the creation and application of tools for learning analytics, so that:

1. a comprehensive view is offered on the different solutions provided by Learning Analytics and which problems they are solving;
2. synergies may emerge from the contributions and view of the participants on the track, and be directed towards the achievement of common goals; and
3. directions on the future developments for Learning Analytics may be pointed out.

Topics

From the above, this Call for Papers is open for relevant contributions covering the following topics:

• Learning Analytics tools:
  • Algorithms and methods for Educational Data Mining
  • Automation of educational processes
  • Educational data visualization
  • Educational decision support systems
  • Educational recommender systems
  • Semantic analysis
  • Social learning analytics
• Educational data and Learning Analytics:
  • Characterization of optimal datasets for Learning Analytics
  • Comparison between small and big educational datasets, including study replications
  • Context dependency of Learning Analytics
  • Educational data-driven decision-making
  • Educational Open Linked Data
  • Learning Analytics for PLEs

Paper language

English

Presentation

The different sessions will be held as panels consisting of a maximum of six presenters, and moderated by the co-chairs.

For each session, authors will briefly present an overview of their submission, with a maximum time allowance of five minutes. This presentation shall not be a summary of the submission but rather a general context of their research.

Following the presentations, the moderators will start a debate with the authors addressing the main contributions of each paper, focusing on common and divergent points. This discussion will have a duration of between forty-five and sixty minutes, and may include active participation from the audience in an open round of questions.

Presentation language: English

Submission

Submission dates: July 7, 2014
Submission format: http://teemconference.eu/submission/
Submissions must be done through  https://www.easychair.org/conferences/?conf=teem2014, choosing this track before to proceed.

Track Scientific Committee

Miguel Ángel Conde-González, Ph.D. (Universidad de León, Spain) – Co-chair.
Ángel Hernández-García, Ph.D. (Universidad Politécnica de Madrid, Spain) – Co-chair
Ángel F. Agudo-Peregrina, Ph.D. (Universidad Politécnica de Madrid, Spain)
Javier Alfonso-Cendón, Ph.D. (Universidad de León, Spain)
Aitor Almeida, Ph.D. (Universidad de Deusto, Spain)
Gustavo Ribeiro Alves, Ph.D. (Instituto Superior de Engenharia do Porto, Portugal)
Weiqin Chen, Ph.D. (Universitetet i Bergen, Norway)
Adam Cooper, Ph.D. (University of Bolton, United Kingdom)
Rebecca Ferguson, Ph.D. (Open University, United Kingdom)
Camino Fernández-Llamas, Ph.D. (Universidad de León, Spain)
Baltasar Fernández-Manjón, Ph.D. (Universidad Complutense de Madrid, Spain)
Ángel Fidalgo-Blanco, Ph.D. (Universidad Politécnica de Madrid, Spain)
Antonio Fumero-Reverón, Ph.D. (Universidad Politécnica de Madrid, Spain)
Francisco José García-Peñalvo, Ph.D. (Universidad de Salamanca, Spain)
Inés González-González, Ph.D. (Universitat Oberta de Catalunya, Spain)
Wolfgang Greller, Ph.D. (Universität Wien, Austria)
David Griffiths, Ph.D. (University of Bolton, United Kingdom)
Santiago Iglesias-Pradas, Ph.D. (Universidad Politécnica de Madrid, Spain)
Ana Isabel Jiménez-Zarco, Ph.D. (Universitat Oberta de Catalunya, Spain)
Mark Johnson, Ph.D. (University of Bolton, United Kingdom)
María Arcelina Marques, Ph.D. (Instituto Superior de Engenharia do Porto, Portugal)
Vicente Matellán-Olivera, Ph.D. (Universidad de León, Spain)
Milos Milovanovic, Ph.D. (Univerzitet u Beogradu, Serbia)
Miroslav Minovic, Ph.D. (Univerzitet u Beogradu, Serbia)
Nic Nistor, Ph.D. (Universität der Bundeswehr München and Ludwig Maximilians Universität München, Germany)
Luis Panizo-Alonso (Universidad de León, Spain)
Abelardo Pardo, Ph.D. (The University of Sydney, Australia)
Salvador Ros-Muñoz, Ph.D. (Universidad Nacional de Educación a Distancia, Spain)
Marcus Specht, Ph.D. (Open Universiteit Nederland, Netherlands)
Roberto Therón, Ph.D. (Universidad de Salamanca, Spain)

Special Issue

The accepted papers in this track will be invited to prepare and submit an extended version to be considered, after a new peer review, for publication in The Scientific World Journal. Special Issue on “Dealing with Complexity: Educational Data and Tools for Learning Analytics” http://www.hindawi.com/journals/tswj/

More info

Dr. Ángel Hernández García
Universidad Politécnica de Madrid
Spain

(+34) 91 5475900 (ext. 2112)
angel.hernandez@upm.es