Case Study

As recommender systems are making inroads to e-learning, the new ecosystem is placing new challenges on them. This Chapter discusses the author’s experiences of adding recommender features to additional reading materials listing page in an undergraduate-level course. Discussion is based on use-log and student questionnaire data. Students could both add materials to lecture readings and peer-evaluate the pertinence of the materials by rating and commenting them. Students were required to add one material and rate five as part of the course requirements. Overall, students perceived the system as useful and did not resent compulsoriness. In addition, perceived social presence promoted social behavior in many students. However, many students rated materials without viewing them, thus undermining the reliability of aggregated ratings. Consequently, while recommenders can enhance the e-learner experience, they need to be robust against some students trying to get points without earning them.

Metis

Recommender systems in e-learning contexts typically try to “intelligently” recommend actions to a learner based on the actions of previous learners. One of the limitations of such systems is that a lot of data is needed in order to recommend meaningful activities. This chapter describes one approach for addressing this limitation in a framework that uses a structured map of mathematics concepts and processes to power a recommender system that will recommend to students digital learning activities for which they are ready. This recommender system is called Metis, for the Greek goddess of good advice, and is currently in the design phase. Metis takes seriously the idea that to build on the knowledge, skills, and abilities (KSAs) that a student has, it is essential to identify those KSAs. Trying to build on KSAs that a student does not have is misguided. Metis recommends activities linked to KSAs that students are ready to learn, and more standard recommender algorithms further refine the list of recommended activities. Taking this approach has the potential to make activities more engaging, which can lead learners to greater interest in the content area.

Providing Recommendations for Mobile Learning

At the interdisciplinary intersection of mobile computing and e-learning, mobile learning is a new paradigm that promises to revolutionize learning by supporting new pedagogical approaches and learning experiences. The unique advantage of mobile learning is to encourage learners to learn in an authentic environment with the help of their mobile devices. In mobile learning systems, recommendation technology can play an important role by providing suitable learning resources to learners according to their interests and preferences. However, the learning needs of learners are dynamically changing as they change their physical location and participate in different activities in the mobile learning environment. Recommendation results cannot reflect actual demands of learners if the learner’s context is ignored. Integrating context into the recommendation process brings along opportunities to better understand the dynamic requirements of learners, but also challenges to constantly improve the existing recommendation mechanism. This chapter aims at providing an overview of these opportunities and challenges.

Clustering of the Web Search Results in Educational Recommender Systems

This chapter presents a meta-search approach, meant to deliver bibliography from the internet, according to trainees’ results obtained at an e-assessment task. The bibliography consists of web pages related to the knowledge gaps of the trainees. The meta-search engine is part of an education recommender system, attached to an e-assessment application for project management knowledge. Meta-search means that, for a specific query (or mistake made by the trainee), several search mechanisms for suitable bibliography (further reading) could be applied. The lists of results delivered by the standard search mechanisms are used to build thematically homogenous groups using an ontology-based clustering algorithm. The clustering process uses an educational ontology and WordNet lexical database to create its categories. The research is presented in the context of recommender systems and their various applications to the education domain.

Context-Aware Recommendations using Topic Maps Technology for the Enhancement of the Creativity Process

Learning can be observed in the creativity process. When this process is supported by a Creativity Support Tool (CST), considering the context in which ideas are developed, as well as the context around the user himself and the task he is carrying out can potentially enhance creativity.The tool’s awareness of such context can be exploited in the offering of useful context-aware recommendations to the users on topics such as relevant resources, people, ideas, projects, et cetera. These recommendations can help users during the creativity process and the learning involved, by providing productive stimuli. In the work presented in this chapter we focus on describing a method for enhancing the creativity process through context-aware recommendations. The method uses ontologies for the knowledge representation of context and the topic maps technology for storing, managing, and delivering content used as recommendations. Furthermore we present the software system that has been developed to support this method in a particular collaborative CST, as well as its evaluation.

Meta-Rule Based Recommender Systems for Educational Applications

Recommendation Systems are central in current applications to help the user find relevant information spread in large amounts of data. Most Recommendation Systems are more effective when huge amounts of user data are available. Educational applications are not popular enough to generate large amount of data. In this context, rule-based Recommendation Systems seem a better solution. Rules can offer specific recommendations with even no usage information. However, large rule-sets are hard to maintain, reengineer, and adapt to user preferences. Meta-rules can generalize a rule-set which provides bases for adaptation. In this chapter, the authors present the benefits of meta-rules, implemented as part of Meta-Mender, a meta-rule based Recommendation System. This is an effective solution to provide a personalized recommendation to the learner, and constitutes a new approach to Recommendation Systems.

Reputation in Peer-Based Learning Environments

This chapter proposes a reputation model to support peer-based learning in online communities. Based on literature on quality, trust, and learning, we argue that a reputation system for peer-based learning environments must at least address quality, context, and sustainability issues. We analyzed a number of successful online reputation systems with these issues, and developed a reputation model to support knowledge management, quality assurance, and increase user engagement in peer-based online learning communities. The description of the model includes a conceptual and mathematical representation, a process description to support implementation, and an evaluation framework. A simple example shows how the model can be applied.

An Ontology Network for Educational Recommender Systems

This chapter presents how an ontology network can be used to explicitly specify the relevant features of Semantic Educational Recommender Systems. This ontology network conceptualizes the different domains and features involved in these kind of systems in a set of interrelated ontologies. Basically, this chapter presents a detailed study of the semantic relationships that exist among the ontologies in the network considering learners and educators goals and taking also into account relevance feedback by users. One important contribution of this work is to show how the ontology-based reasoning mechanism can be used to validate the recommendation criteria and to assure flexibility for tailoring the educational resource adequacy features (called Educational Resource Quality).

Challenges to Use Recommender Systems to Enhance Meta-Cognitive Functioning in Online Learners

A wealth of research has shown that meta-cognition plays a crucial role in the promotion of effective school learning. In most of the e-learning environment designs, however, meta-cognitive strategies have generally been neglected, and therefore, satisfactory uses of these strategies have rarely been realized. Most learners are not even aware of what they have been studying. If the learning system could automatically guide and intelligently recommend learning activities or strategies to facilitate student monitoring and control of their learning, it would favor and improve their learning process and performance. Unfortunately, nearly no e-learning systems to date have attempted to do so. In this chapter, we first described the need for enhancing meta-cognitive skills in e-learning environment, followed by an outline of major challenges for meta-cognitive activity recommendations. We then proposed to adopt data mining algorithms (i.e., content-based and sequence-based recommendation techniques) to meet the identified issues with a toy example.

A Systematic Approach for Designing Educational Recommender Systems

The construction of Educational Recommender System (ERS) demands the incorporation of quality attributes at the software design, such as availability for preventing the service to be unavailable for a long time, and scalability for preventing the system from going offline due to a large number of simultaneous requests. The incorporation of such characteristics makes ERS more complex and expensive, but existing strategies for designing ERS do not consider quality attributes in an explicit way. This chapter presents an architecture-centered solution, which is partially supported by tools and considers quality attributes as early as possible in the software development process in a systematic way, from requirements to the source code. The feasibility of the proposed process is showed in terms of a case study executed in a “step-by-step” fashion, presenting how the software architecture can be designed and gradually refined until it achieves the level of object-oriented classes generated based on design patterns.