Special Issue – September 2019 on “Learning Analytics and Educational Research”


Special Issue – September 2019 on “Learning Analytics and Educational Research”

Guest Editors: Roberto Trinchero (University of Turin, Italy), Luciano Cecconi (University of Modena and Reggio Emilia, Italy)

Initial manuscripts due: 20th July, 2019
Notification and Review Comments: 3rd September, 2019
Camera Ready manuscript due: 20th September, 2019
Special Issue published: September, 2019


This call for papers aims to gather contributions of a theoretical, empirical and comparative nature that address the issues of the International Conference “Learning Analytics. For a dialogue between teaching practices and educational research”, organized by SIRD and SIe-L and held in Rome on 10 and 11 May 2019, from an educational and didactic point of view.
To delimit the research field to which the call refers, we refer to the definition of Learning Analytics (LA) adopted by the 1st International Conference on Learning Analytics (2011) and widely shared by the international community: “Learning analytics is the measurement, collection, analysis, and reporting of data about learners and their contexts, for the purposes of understanding and optimizing learning and the environments in which it occurs” (Siemens, 2013). Within these limits and in accordance with these aims, over the last few years numerous experiences have developed around the world and a very promising field of research has been established.
The challenges that the LA pose to the educational contexts and to educational research are many: it is about building strong links with the sciences of education, developing working methods with diversified data sets in order to optimize learning environments, focus on student perspectives, develop and apply a clear set of ethical guidelines (Ferguson, 2014). These are all challenges that involve educational research to investigate the possible use of LA at different institutional levels, from single classrooms, departments, universities, national and international levels (Buckingham Shum, 2012) and for different purposes: descriptive, diagnostic, predictive, prescriptive (Gartner, 2013). It can be useful to use LA to reflect on what happened in a given learning context, why this happened, what might happen (for example, identifying students at risk) and what should be done to improve student learning and the quality of environments.
Before the spread of digital learning environments these data were not available, in terms of quantity and quality, as they are today. Currently these data can help to enrich the empirical basis of educational research but also to make the analysis methods more complex and more powerful.
There are several areas of educational research that could benefit greatly from an intelligent use of LA. Just think, to give two examples, to the evaluation and the need to shift his attention from the product of the training action to his process, or to the many possibilities that open up in favor of the individualization of learning paths thanks to the great availability of real-time data on individual routes.
How to finalize the collection and analysis of the many data available today is the most important challenge that educational research faces. It is an important occasion to which this call aims to make a small contribution.


  • Learning Analytics, from macro to micro: the use of LA from the level of educational policies to the academic level up to that of the single course and the individual student.
  • Learning Analytics and digital learning environments: how to make data visible for students and teachers (dashboards).
  • Learning Analytics and instructional design: designing the collection and report of data and using data to design effective training paths.
  • Learning Analytics and learning contexts (formal, non-formal and informal)
  • Learning Analytics and evaluation processes: from the product to the process
  • Learning Analytics and certification: open badges
  • Learning Analytics and individualization of learning paths
  • Learning Analytics and identification of students at risk
  • Learning Analytics and educational success


  • Buckingham Shum, S. (2012). Learning analytics. UNESCO policy brief. Retrieved from http://iite.unesco.org/pics/publications/en/files/3214711.pdf
  • Ferguson R. (2014). Learning Analitycs: fattori trainanti, sviluppi e sfide, TD Tecnologie didattiche, 22 (3), 138-147
  • Gartner (2013): Top 10 Moments from Gartner’s Supply Chain Executive Conference, https://blogs.gartner.com/matthew-davis/top-10-moments-from-gartners-supply-chain-executive-conference/
  • Siemens G. (2013), Learning Analytics: The Emergence of a Discipline, American Behavioural Scientist, 57 (10), pp. 1380-1400, Sage Pubblication.


It is possible to submit proposals in the following three sections:

  • Researches (max. 40,000 characters, spaces included);
  • Experiences (max. 30,000 characters, spaces included);
  • Studies (max. 30,000 characters, spaces included).


Language: Italian, English.
Author Guidelines
All submitted papers will be subject to a selection mechanism based on a double blind review.

Click here to download the call for paper as a pdf file.