Zoran Jeremic

Student modeling and assessment in intelligent tutoring of software patterns

This paper presents the design, implementation, and evaluation of a student model in DEPTHS (Design Pattern Teaching Help System), an intelligent tutoring system for learning software design patterns. There are many approaches and technologies for student modeling, but choosing the right one depends on intended functionalities of an intelligent system that the student model is going to be used in. Those functionalities often determine the kinds of information that the student model should contain. The student model used in DEPTHS is a result of combining two widely known modeling approaches, namely, stereotype and overlay modeling. The model is domain independent and can be easily applied in other learning domains as well. To keep student model update during the learning process, DEPTHS makes use of a knowledge assessment method based on fuzzy rules (i.e., a combination of production rules and fuzzy logics). The evaluation of DEPTHS performed with the aim of assessing the systems overall effectiveness and the accuracy of its student model, indicated several advantages of the DEPTHS system over the traditional approach to learning design patterns, and encouraged us to move on further with this research.

A metrics-driven approach for quality assessment of linked open data

The main objective of the Web of Data paradigm is to crystallize knowledge through the interlinking of already existing but dispersed data. The usefulness of the developed knowledge depends strongly on the quality of the published data. Researchers have observed many deficiencies with regard to the quality of Linked Open Data. The first step towards improving the quality of data released as a part of the Linked Open Data Cloud is to develop tools for measuring the quality of such data. To this end, the main objective of this paper is to propose and validate a set of metrics for evaluating the inherent quality characteristics of a dataset before it is released to the Linked Open Data Cloud. These inherent characteristics are semantic accuracy, syntactic accuracy, uniqueness, completeness and consistency. We follow the Goal-Question-Metric approach to propose various metrics for each of these five quality characteristics. We provide both theoretical validation and empirical observation of the behavior of the proposed metrics in this paper. The proposed set of metrics establishes a starting point for a systematic inherent quality analysis of open datasets.

Design pattern ITS: student model implementation

The paper presents implementation of the student model in the design pattern intelligent tutoring system. The student model is created by using a model template which is filled in with new attribute values. The same principle can be applied to other ITS as well.

Personal learning environments on the Social Semantic Web

Todays students, being used to constant activity and multitasking in their everyday life, need a high level of social and creative engagement in order to learn; for them, highly interactive learning environments which allow for communication, collaboration, and authoring, are a must. In addition, modern learning theories stress the importance of interactivity and engagement of students for successful learning processes, whereas recent empirical studies provide evidence and confirm this. In this paper, we present how the integration of Social and Semantic Web technologies, often referred to as the Social Semantic Web SSW, along with the Linked Data paradigm offer potentials for improving the interactivity of todays learning environments, while putting students in control of their learning process spanning across different tools and services. We identify the main principles on which such SSW-supported personal learning environments are based, and illustrate them through the design, implementation, analysis, and evaluation of DEPTHS DEsign Patterns Teaching Help System --a SSW-based interactive personal learning environment we have developed for the domain of software design patterns.

Automated Semantic Tagging of Textual Content

Motivated by a continually increasing demand for applications that depend on machine comprehension of text-based content, researchers in both academia and industry have developed innovative solutions for automated information extraction from text. In this article, the authors focus on a subset of such tools--semantic taggers--that not only extract and disambiguate entities mentioned in the text but also identify topics that unambiguously describe the texts main themes. The authors offer insight into the process of semantic tagging, the capabilities and specificities of todays semantic taggers, and also indicate some of the criteria to be considered when choosing a tagger.

Learn-B: a social analytics-enabled tool for self-regulated workplace learning

In this design briefing, we introduce the Learn-B environment, our attempt in designing and implementing a research prototype to address some of the challenges inherent in workplace learning: the informal aspect of workplace learning requires knowledge workers to be supported in their self-regulatory learning (SRL) processes, whilst its social nature draws attention to the role of collective in those processes. Moreover, learning at workplace is contextual and on-demand, thus requiring organizations to recognize and motivate the learning and knowledge building activities of their employees, where individual learning goals are harmonized with those of the organization. In particular, we focus on the analytics-based features of Learn-B, illustrate their design and current implementation, and discuss how each of them is hypothesized to target the above challenges.

Leveraging semantic technologies for harmonization of individual and organizational learning

For a successful learning organization, it is of crucial importance to have successful methods for stimulation and sharing of working and learning activities of their employees. However, there are two important challenges to be addressed: i) combination of individual and organizational incentives that motivate employees to take part in knowledge building and sharing activities; and ii) structuring of learning and knowledge building activities and their outcomes in a representation that can assure unambiguous knowledge sharing. To address these challenges, we propose a framework of individual and organizational factors for knowledge sharing and a set of ontologies that provides a systematic and interlinked representation of concepts of individual and organizational learning. On top of these proposals, we developed and here present a software solution, which has been evaluated through a case study conducted in a large enterprise context.

Project-Based Collaborative Learning Environment with Context-Aware Educational Services

Teaching and learning software design patterns (DPs) is not an easy task. Apart from learning individual DPs and the principles behind them, students should learn how to apply them in real-life situations. Therefore, to make the learning process of DPs effective, it is necessary to include a project component in which students, usually in small teams, develop a medium-sized software application. Furthermore, it is necessary to provide students with means for easy discovery of relevant learning resources and possible collaborators. In this paper, we propose an extensive project-based collaborative learning environment for learning software DPs that integrates several existing educational systems and tools based on the common ontological foundation. The learning process in the suggested environment is further facilitated and augmented by several context-aware educational services.

Online Presence in Adaptive Learning on the Social Semantic Web

In adaptive learning environments, this exchangeof online presence data cannot be considered isolatedfrom the overall learning context. However, there isyet no systematic solution to exchanging andintegrating online presence data from diverse instantmessaging and social networking applications. Toaddress this issue, we propose an ontology-basedapproach to sharing online presence data in adaptivelearning environments through the use of the OnlinePresence Ontology. This ontology is integrated into theLearning Object Context Ontology framework, whichallows for capturing and unambiguous representationof all relevant data about students online presence,their mutual interactions, as well as their interactionswith learning resources. On top of this ontologyframework, we have developed innovative, context-awarelearning services presented in this paper. Theuse of these services is demonstrated in a learningenvironment for studying software patterns.

An empirical evaluation of ontology-based semantic annotators

One of the most important prerequisites for achieving the Semantic Web vision is semantic annotation of data/resources. Semantic annotation enriches unstructured and/or semistructured content with a context that is further linked to the structured domain-specific knowledge. In particular, ontologybased semantic annotators enable the selection of a specific ontology to annotate content. This paper presents results of an empirical study of recent ontology-based annotators, namely Stanbol, KIM, and SDArch. Specifically, we evaluated the robustness of these annotators with respect to specific features of ontology concepts such as the length of concepts? labels and their linguistic categories (e.g., prepositions and conjunctions). Our results show that although significantly correlated according to most of the conducted evaluations, tools still exhibit their unique features that could be a topic of new research.