Editorial: A Message from the Editorial Team and an Introduction to the April-June 2017 issue

WELCOME to the second 2017 issue of the IEEE Transactions on Learning Technologies. The issue starts with the introduction of the new cohort of Associate Editors. We are excited to bring in nine new editorial board members who will help us to assess the increasing flow of high-quality submissions while also bringing expertise in several popular and emerging areas such as augmented reality, MOOCs, gamification, and learning analytics. The expertise profiles of the new Associate Editors are presented in the next section. Please, join us in welcoming them to the journal team! This first regular issue of 2017 uses the expanded page budget to present 10 papers on popular topics in the area of Learning Technologies. In “Adaptive Social Learning Based on Crowdsourcing”, Evgeny Karataev and Vladimir Zadorozhny show how to combine learner-contributed content, social networked learning, and personalization. They describe the SALT system that enables students to contribute and consume mini-lessons (or ‘lesslets’) comprising name, explanation of concept, brief example and test of understanding. Lesslets can stand alone, or can be built into learning pathways. SALT automatically sequences these for each learner based on estimated difficulty derived from user’s test scores. In a trial with 260 undergraduate and graduate students, the students contributed about 300 lesslets, as well as commenting and voting on each other’s contributions. The system was able to identify clusters of students with similar learning patterns and use these to perform personalization. Providing individualized learning in open-ended environments, where students can explore alternative solution paths, is a challenge for learning technology. In their paper “Integrating Model-Driven and Data-Driven Techniques for Analyzing Learning Behaviors in Open-Ended Learning Environments”, John S. Kinnebrew, James R. Segedy andGautam Biswas bring together two previous approaches: model-based analysis of students’ activity sequences and data-driven pattern discovery. The strategymodel determines how to analyze learner behavior and data-driven analysis of frequent learner activity extends the strategy model. This combined approach was applied in the Betty’s Brain system for students to learn science by constructing causal models. The paper reports data from a study with 68 sixth-grade students. It showed no significant effect of treatment, however the pattern-mining approach identified new variations of strategies and gaps in themodel. Model construction is also the topic of the paper by Kurt VanLehn, JonWetzel, Sachin Grover, and Brett van de Sande on “Learning How to Construct Models of Dynamic Systems: An Initial Evaluation of the Dragoon Intelligent Tutoring System”. Dragoon is designed to teach high school and college students to construct models of dynamic systems (such as changes in animal population) through four modes: edit a model, test the output of a model, gain immediate feedback on a new entry in the model, and be coached through process advice on what steps to do next. An evaluation compared 16 students receiving computer-based coaching (Tutor) from Dragoon with 18 students who used it for editing only (Editor). The mean exam scores for the two groups were not significantly different, but a comparison of those students who made high use of the system (in either condition) showed better performance for the Tutor group. In “Cognitive Diffusion Model: Facilitating EFL Learning in an Authentic Environment”, Rustam Shadiev, Wu-Yuin Hwang, Yueh-Min Huang, and Tzu-Yu Liu describe a mobile learning system that enables students to learn a foreign language by taking pictures of objects, describing them in writing, and then sharing their work with peers. The students are introduced to a topic in class, then go outside to apply their knowledge. An evaluation with 57 junior high school students compared an experimental group that used the system on tablet computers with a control group that were set a traditional learning approach using textbooks, making notes and taking pictures of objects. The two groups showed similar performance in tasks to remember words, but the experimental group performed better in test items to understand and apply knowledge. The affordances of mobile devices are also explored in a paper by David Cabielles-Hern andez, Juan-Ram on P erez-P erez, MPuerto Paule-Ruiz, and Samuel Fern andez-Fern andez with the title “Specialized Intervention Using Tablet Devices for Communication Deficits in Children with Autism Spectrum Disorders”. This describes the Chain of Words system to help young children with autism communicate by learning how to build sentences, pronounce them and extend their skills in grammar, syntax and phonetics. The system was tested with eleven children aged three to eight, with data recorded from