Special Issue on Learning analytics and Recommendation

IJIMAI

International Journal of Interactive Multimedia and Artificial Intelligence

http://www.ijimai.org/journal/home

 Special Issue on Learning analytics and Recommendation

 

The UNESCO Chair on eLearning at the International University of La Rioja (UNIR) is invited as guest editor of this special issue, focused on Learning analytics and Recommendation, which will provide an up-to-date overview on the topic, and the connection between personalized learning in formal, non-formal and informal settings, with analytics techniques supported by information retrieval, categorization, visualization of user interaction, user performance, and other input from students and teachers. Contributions are welcome as presented below

 

Guest editors

Dr. Luis de-la-Fuente Valentín
Senior Researcher
Universidad Internacional de La Rioja

Prof. Dr. Daniel Burgos
Vice-chancellor for Research & Technology
UNESCO Chair on eLearning
Universidad Internacional de La Rioja

Dr. Riccardo Mazza
Lecturer and researcher at the University of Applied Sciences
Southern Switzerland and University of Lugano

Background

Current education is far from the old fashioned instructive approach, where the students were simple passive receptors of the information. Now, active learning involves students in the course activities following a more constructivist paradigm, and it is therefore a much more student centered education. A side effect is the need to keep the course alive by having in mind the individual needs of each student. To accomplish such goal, teachers have to observe what happens in the course, then extract conclusions and finally react according to the observations. Teaching is now much more about observing than it was in the past.

But the teacher is not alone in this duty; several machine learning strategies are able to support practitioners in the monitorization, analysis and reaction to course events. In current research, such techniques are under the umbrella of the Learning Analytics research field. Data mining, artificial intelligence and statistical analysis techniques go beyond the raw data and are used to describe and understand facts and processes in the course context. Learning Analytics tools help understanding what happens in the course and enables the human judgment to take the final decision and execute the actions, while the automated discovery is threated just as a supporting tool.

Learning Analytics strategies are suitable for a wide range of learning scenarios and goal. They can be targeted to students, usually by using information visualization mechanisms that provide feedback to the students and increase awareness and push self-reflection skills. They can also be targeted to teachers, usually devoted to detect abnormal situations or students at risk. The Learning Analytics research field has a great potential and many possible applications in the education field: group management, grade predictions, goal tracking, et cetera. Both students and teachers can receive timely recommendations for an effective support in their daily tasks.

Despite the increasing research interest on Learning Analytics, few evidences of its impact on real learning scenarios are available in the literature. This special issue focuses its attention in both excellent outcomes with evidence of its impact in the end user of a real scenario, and also in research directions that will lead innovation in the near future of Learning Analytics techniques. A particular stress will be on the empirical validation of the presented analytics systems and their role in the decision making process.

Furthermore, Learning Analytics deal with a large number of data which can be used not just to find user patterns and social behaviours, but to provide recommendation to the user about the next action to take, the learning itinerary, the right content, or the appropriate level of presentation. In this context, Learning Analytics become the tool for the advanced service of personalized learning, from individual to group approaches. In turn, the frequent use of the recommender service will train the very same system, and will provide useful feedback to the analytical part of the couple. In this context, analytics and recommendation become a bi-directional supported marriage, where information flows back and forth, depending on the role played along the full process.

Topics

This special issue is interested focused (but not limited to) the following research topics:

Pedagogy and didactics

  • adaptive elearning processes and Learning analytics
  • informal and formal learning, combined
  • personalized learning and customisation of Learning analytics
  • personal learning paths and the influence of Learning analytics
  • Learning analytics used in personalized eLearning processes
  • Learning analytics and the blended-learning approach
  • pedagogical models behind Learning analytics and Recommendation
  • benefits, drawbacks, difficulties and challenges while using Learning analytics in recommender systems
  • theoretical research on implications of recommendation in learning acquisition and behaviour
  • information retrieval and analysis of big data as input cycle for recommender systems
  • Learning analytics, Recommendation and learning styles
  • Learning analytics, Recommendation and collaborative learning
  • assessment and grading in Learning analytics
  • teaching with Learning analytics

Practical experience, experimentation and development

  • practical experiences in classroom
  • running prototypes and practical demos
  • hands-on applications
  • personal competence development
  • methodologies to create Learning analytics and personalized processes
  • students and teachers as users of Learning analytics

Standards, ontologies and industry

  • Learning analytics, Recommendation and Learning Objects
  • Learning analytics, Recommendation and eLearning standards (i.e., IMS Learning Design, SCORM…)
  • Learning analytics, Recommendation and eLearning systems (i.e., Moodle, Blackboard, LAMS…)
  • Learning analytics, Recommendation and Social Networks
  • re-purposing existing Learning analytics for adaptive eLearning objectives
  • commercial Learning analytics and Recommendation used in eLearning environments
  • synergies between the educational and gaming industries, on the matter
  • Use of tablets and mobile devices for personalized learning through information retrieval and analysis

About IJIMAIThe International Journal of Interactive Multimedia and Artificial Intelligence – IJIMAI (ISSN 1989 – 1660) provides an interdisciplinary forum in which scientists and professionals can share their research results and report new advances on AI tools or tools that use AI with interactive multimedia techniques.

IJIMAI is indexed by Web of Knowledge, Inspec, Publindex, DBLP, Latindex, ABSCO, Dialtnet, and others. Full list at http://www.ijimai.org/journal/indexed.