Learner modelling: systematic review of the literature from the last 5 years

The field of adaptive e-learning is continuously developing. More research is being conducted in this area as adaptive e-learning aims to provide learners with adaptive learning paths and content, according to their individual characteristics and needs, which makes e-learning more efficient and effective. The learner model, which is a representation of different learner’s characteristics, plays a key role in this adaptation. This paper presents a systematic literature review about learner modelling during the last 5 years, describing the different modelled characteristics and the adopted modelling techniques and modeling types: automatic modeling and collaborative modeling. 107 publications were selected and analyzed, and six categories of the modelled characteristics were identified. This literature review contributes to the identification of the learners’ individual traits and presents the most used modelling techniques for each of them. It also identifies the latest research trends of Learner Modeling and generates future research directions in this field.

     

Delivering audiovisual content with MPEG-21-enabled cross-layer QoS adaptation

Future multimedia communication systems have to support the user‘s needs, the terminal capabilities, the content specification and the underlying networking technologies. The related protocols and applications must be designed from this integration perspective in a cross-layer centric manner. In this paper, we propose an implementation of a streaming service (e.g.,Television over IP service) with a unified QoS management concept that enables an IP driven integration of different system components (terminal, user, content, and network). The MPEG-21 framework is used to provide a common support for implementing and managing the end-to-end QoS. The main focus of this paper is on the architecture design, protocols specification and implementation evaluation. Performance evaluations using PSNR and SSIM objective video quality metrics show the benefit of the proposed MPEG-21-enabled cross-layer adaptation.     

Modelling within-person idiographic variance could help explain and individualize learning

Learning analytics is a fast-growing discipline. Institutions and countries alike are racing to harness the power of using data to support students, teachers and stakeholders. Research in the field has proven that predicting and supporting underachieving students is worthwhile. Nonetheless, challenges remain unresolved, for example, lack of generalizability, portability and failure to advance our understanding of students' behaviour. Recently, interest has grown in modelling individual or within-person behaviour, that is, understanding the person-specific changes. This study applies a novel method that combines within-person with between-person variance to better understand how changes unfolding at the individual level can explain students' final grades. By modelling the within-person variance, we directly model where the process takes place, that is the student. Our study finds that combining within- and between-person variance offers a better explanatory power and a better guidance of the variables that could be targeted for intervention at the personal and group levels. Furthermore, using within-person variance opens the door for person-specific idiographic models that work on individual student data and offer students support based on their own insights.

Practitioner notes

What is already known about this topic

• Predicting students' performance has commonly been implemented using cross-sectional data at the group level.
• Predictive models help predict and explain student performance in individual courses but are hard to generalize.
• Heterogeneity has been a major factor in hindering cross-course or context generalization.

What this paper adds

• Intra-individual (within-person) variations can be modelled using repeated measures data.
• Hybrid between–within-person models offer more explanatory and predictive power of students' performance.
• Intra-individual variations do not mirror interindividual variations, and thus, generalization is not warranted.
• Regularity is a robust predictor of student performance at both the individual and the group levels.

Implications for practice

• The study offers a method for teachers to better understand and predict students' performance.
• The study offers a method of identifying what works on a group or personal level.
• Intervention at the personal level can be more effective when using within-person predictors and at the group level when using between-person predictors.

     

The role of design ethics in maintaining students' privacy: A call to action to learning designers in higher education

Maintaining students' privacy in higher education, an integral aspect of learning design and technology integration, is not only a matter of policy and law but also a matter of design ethics. Similar to faculty educators, learning designers in higher education play a vital role in maintaining students' privacy by designing learning experiences that rely on online technology integration. Like other professional designers, they need to care for the humans they design for by not producing designs that infringe on their privacy, thus, not causing harm. Recognizing that widely used instructional design models are silent on the topic and do not address ethical considerations such as privacy, we focus this paper on how design ethics can be leveraged by learning designers in higher education in a practical manner, illustrated through authentic examples. We highlight where the ethical responsibility of learning designers comes into the foreground when maintaining students' privacy and well-being, especially in online settings. We outline an existing ethical decision-making framework and show how learning designers can use it as a call to action to protect the students they design for, strengthening their ethical design capacity.

Practitioner notes

What is already known about this topic

• Existing codes of ethical standards from well-known learning design organizations call upon learning designers to protect students' privacy without clear guidance on how to do so.
• Design ethics within learning design is often discussed in abstract ways with principles that are difficult to apply.
• Most, if not all, design models that learning design professionals have learned are either silent on design ethics and/or do not consider ethics as a valid dimension, thus, making design ethics mostly excluded from learning design graduate programs.
• Practical means for engaging in ethical design practice are scarce in the field.

What this paper adds

• A call for learning designers in higher education to maintain and protect students' privacy and well-being, strengthening their ethical design capacity.
• A demonstration of how to use a practical ethical decision-making framework as a designerly tool in designing for learning to maintain and protect students' privacy and well-being.
• Authentic examples—in the form of vignettes—of ethical dilemmas/issues that learning designers in higher education could face, focused on students' privacy.
• Methods—using a practical ethical decision-making framework—for learning design professionals in higher education, grounded in the philosophy of designers as the guarantors of designs, to be employed to detect situations where students' privacy and best interests are at risk.
• A demonstration of how learning designers could make stellar design decisions in service to the students they design for and not to the priorities of other design stakeholders.

Implications for practice and/or policy

• Higher education programs/institutions that prepare/employ learning designers ought to treat the topics of the designer's responsibility and design ethics more explicitly and practically as one of the means to maintain and protect students' privacy, in addition to law and policies.
• Learning designers in higher education ought to hold a powerful position in their professional practice to maintain and protect students' privacy and well-being, as an important aspect of their ethical design responsibilities.
• Learning designers in higher education ought to adopt a design thinking mindset in order to protect students' privacy by (1) challenging ideas and assumptions regarding technology integration in general and (2) detecting what is known in User Experience (UX) design as “dark patterns” in online course design.

     

ECRIMO,an app to train first graders' spelling: Effectiveness and comparison between different designs

The present study assessed the effectiveness of the ECRIMO educational application designed to build first-grade level spelling skills. We tested whether using the app to teach spelling would be as effective as providing the same training using traditional paper exercises. The effect of integrating gamification into mobile learning apps, which has been little studied in the context of young children, is also investigated. A pretest/training/posttest design was implemented with 311 first-graders divided in four groups: no training, paper training, the ECRIMO app with gamification features, and the ECRIMO app without gamification. Spelling, reading and phonological awareness abilities was measured at both pretest and posttest. The training was conducted over a 7-week period (4.40 hours in total). The experimental design allowed us to answer three questions: (1) Is spelling training effective regardless of the medium used? (2) Is training through the app as efficient as paper-based training? (3) Does gamification impact students' learning performance? Mixed-model analyses revealed (1) a positive effect on the training outcome depended on the initial spelling ability of participants, (2) a comparable efficiency between autonomous training using the ECRIMO app on tablets and the same training provided by teachers using paper exercises and (3) a marginally positive effect of gamification that is greater for the weakest students. The present study proposes an original and pertinent experimental design to test the relevance of educational applications. The design features of learning apps can impact students' learning differently depending on their initial level. A critical step should be verifying that using online apps for training is at least as effective as the same training using paper exercises.

Practitioner notes

What is already known about this topic

• A significant number of children experience difficulties in reading and spelling from the first years of learning.
• The use of new technologies to support classroom teaching is rapidly developing as a topic of interest for educational professionals and researchers.
• Evaluations of new technologies developed to enhance literacy skills suggest that many factors can vary their effectiveness.
• The effectiveness of a digital educational application can be enhanced or undermined by design choices, such as gamification.

What this paper adds

• Spelling training with the app ECRIMO seems effective for first year students, especially those with the lowest and middle level.
• Comparable effects of both the tablet-based and paper equivalent training on participants' spelling were found.
• The use of gamification in ECRIMO could be more suitable for the weakest students.

Implications for practice and/or policy

• Educational technologies should be evidence-based and should be evaluated with both a passive and an active control group.
• The design should be carefully considered and tested, as it may be advantageous for some students and disadvantageous for others.
• The use of digital technology in education can be beneficial for classroom practice, when the activity can be carried out in total autonomy, leaving the teacher available for a group of pupils with specific needs.