Boban Vesin

Protus 2.0: Ontology-based semantic recommendation in programming tutoring system

With the development of the Semantic web the use of ontologies as a formalism to describe knowledge and information in a way that can be shared on the web is becoming common. The explicit conceptualization of system components in a form of ontology facilitates knowledge sharing, knowledge reuse, communication and collaboration and construction of knowledge rich and intensive systems. Semantic web provides huge potential and opportunities for developing the next generation of e-learning systems. In previous work, we presented tutoring system named Protus (PRogramming TUtoring System) that is used for learning the essence of Java programming language. It uses principles of learning style identification and content recommendation for course personalization. This paper presents new approach to perform effective personalization highly based on Semantic web technologies performed in new version of the system, named Protus 2.0. This comprises the use of an ontology and adaptation rules for knowledge representation and inference engines for reasoning. Functionality, structure and implementation of a Protus 2.0 ontology as well as syntax of SWRL rules implemented for on-the-fly personalization will be presented in this paper.

Rule-Based reasoning for building learner model in programming tutoring system

Semantic Web provides huge potential and opportunities for developing the next generation of e-learning systems. Although ontologies have a set of basic implicit reasoning mechanisms derived from the description logic, they need rules to make further inferences and to express relations that cannot be represented by ontological reasoning. We implemented an adaptive and intelligent web-based PRogramming TUtoring System --- Protus. One of the most important features of Protus is the adaptation of the presentation and navigation of a course material based on particular learner knowledge. This system aims at automatically guiding the learners activities and recommend relevant actions during the learning process. This paper describes the functionality, structure and implementation of a learner model used in Protus as well as syntax of SWRL rules implemented for on-the-fly update of learner model ontology.

Personalisation of Programming Tutoring System Using Tag-Based Recommender Systems

Collaborative tagging systems have grown in popularity over the Web in the last years based on their simplicity to categorize and retrieve content using open-ended tags. Besides helping user to organize his/her personal collections, a tag also can be regarded as a users or experts personal opinion expression. Thus, the tagging information can be used to make recommendations. In this paper, an innovative architecture for a tag-based recommender system dedicated to the e-learning environments is introduced. This system could support learners by recommending tags and learning resources, online learning activities or optimal browsing pathways, based on their preferences, learning style, knowledge level and the browsing history of other learners with similar characteristics.

Social tagging strategy for enhancing e-learning experience

Abstract Success of e-learning systems depends on their capability to automatically retrieve and recommend relevant learning content according to the preferences of a specific learner. Learning experience and dynamic choice of educational material that is presented to learners can be enhanced using different recommendation techniques. As popularity of collaborative tagging systems grows, users’ tags could provide useful information to improve recommender system algorithms in e-learning environments. In this paper, we present an approach for implementation of collaborative tagging techniques into online tutoring system. The implemented approach combines social tagging and sequential patterns mining for generating recommendations of learning resources to learners. Several experiments were carried out in order to verify usability of the proposed hybrid method within e-learning environment and analyze selected social tagging techniques.

OctoUML: an environment for exploratory and collaborative software design

Software architects seek efficient support for planningand designing models at multiple levels of abstraction andfrom different perspectives. For this it is desirable that softwaredesign tools support both informal and formal representation ofdesign, and also support their combination and the transitionbetween them. Furthermore, software design tools should beable to provide features for collaborative work on the design.OctoUML supports the creation of software models at variouslevels of formality, collaborative software design, and multi-modalinteraction methods. By combining these features, OctoUML isa prototype of a new generation software design environmentthat aims to better supports software architects in their actualsoftware design and modelling processes. Demo video URL: https://youtu.be/fsN3rfEAYHw. OctoUML Project URL: https://github.com/Imarcus/OctoUML.

Enhancing e-learning systems with personalized recommendation based on collaborative tagging techniques

Personalization of the e-learning systems according to the learner’s needs and knowledge level presents the key element in a learning process. E-learning systems with personalized recommendations should adapt the learning experience according to the goals of the individual learner. Aiming to facilitate personalization of a learning content, various kinds of techniques can be applied. Collaborative and social tagging techniques could be useful for enhancing recommendation of learning resources. In this paper, we analyze the suitability of different techniques for applying tag-based recommendations in e-learning environments. The most appropriate model ranking, based on tensor factorization technique, has been modified to gain the most efficient recommendation results. We propose reducing tag space with clustering technique based on learning style model, in order to improve execution time and decrease memory requirements, while preserving the quality of the recommendations. Such reduced model for providing tag-based recommendations has been used and evaluated in a programming tutoring system.

Personal Assistance Agent in Programming Tutoring System

E-learning systems must use different technologies to change the educational environment and perform the adaptation of educational material according to the needs of learners. Popular approach in designing and developing adaptive courses include employment of different kinds of personalized agents. In our previous research, we implemented a tutoring system named Protus (PROgramming TUtoring System) that is used for learning programming basics. This paper presents the architecture and methodology for implementation of personal assistance agent in programming tutoring system that dynamically tracks actions of the learner, determines his/her learning styles and adapts educational material and user interface to assigned individual. The role of the personalized agent will be to collect data on assigned learner, track his/her actions, learning styles and the results achieved in the tests. In a further process, the agent consults personal agents of other learners that have the same learning style. The engaged agent determines what actions and teaching materials brought the most benefit to these learners and in further learning process generates and displays the recommendations of the best ranked actions and materials to assigned learner. The main pedagogical objective of the personal assistance agent in Protus is to present learners the appropriate educational material, tailored to their learning style in order to efficiently and quickly learn the content.

Improving testing abilities of a programming tutoring system

Testing of learners knowledge is demanding functionality of the e-learning systems. Multiple choice questions are suitable and easy to implement feature for testing the knowledge in systems for learning social studies. However, these questions are not suitable for systems for learning the basics of programming problems where solutions are not exact. In previous work we have presented the basic functionalities of the Protus system that implements Java programming course for beginners. Testing knowledge in this system is implemented through various tests with numerous multiple-choice questions. The aim of this paper is to present integration of the existing automatic assessment tool named Testovid within Protus system in order to achieve advanced testing functionalities in solving programming tasks.