Nicola Capuano

Adaptive course generation through learning styles representation

This paper presents an approach to automatic course generation and student modeling. The method has been developed during the European funded projects Diogene and Intraserv, focused on the construction of an adaptive e-learning platform. The aim of the platform is the automatic generation and personalization of courses, taking into account pedagogical knowledge on the didactic domain as well as statistic information on both the student’s knowledge degree and learning preferences. Pedagogical information is described by means of an innovative methodology suitable for effective and efficient course generation and personalization. Moreover, statistic information can be collected and exploited by the system in order to better describe the student’s preferences and learning performances. Learning material is chosen by the system matching the student’s learning preferences with the learning material type, following a pedagogical approach suggested by Felder and Silverman. The paper discusses how automatic learning material personalization makes it possible to facilitate distance learning access to both able-bodied and disabled people. Results from the Diogene and Intraserv evaluation are reported and discussed.

LIA: An Intelligent Advisor for E-Learning

Intelligent e-learning systems have revolutionized online education by providing individualized and personalized instruction for each learner. Nevertheless, until now very few systems were able to leave academic laboratories and be integrated into real commercial products. One of these few exceptions is the Learning Intelligent Advisor (LIA) described in this article, built on results coming from several research projects and currently integrated in a complete e-learning solution named Intelligent Web Teacher (IWT). The purpose of this article is to describe how LIA works and cooperates with IWT in the provisioning of individualized e-learning experiences. Defined algorithms and underlying models are described as well as architectural aspects related to the integration in IWT. Results of experimentations with real users are discussed to demonstrate the benefits of LIA as an add-on in online learning.

Wide field imaging – I. Applications of neural networks to object detection and star/galaxy classification

Astronomical wide-field imaging performed with new large-format CCD detectors poses data reduction problems of unprecedented scale, which are difficult to deal with using traditional interactive tools. We present here NExt (Neural Extractor), a new neural network (NN) based package capable of detecting objects and performing both deblending and star/galaxy classification in an automatic way. Traditionally, in astronomical images, objects are first distinguished from the noisy background by searching for sets of connected pixels having brightnesses above a given threshold; they are then classified as stars or as galaxies through diagnostic diagrams having variables chosen according to the astronomers taste and experience. In the extraction step, assuming that images are well sampled, NExt requires only the simplest a priori definition of ‘what an object is’ (i.e. it keeps all structures composed of more than one pixel) and performs the detection via an unsupervised NN, approaching detection as a clustering problem that has been thoroughly studied in the artificial intelligence literature. The first part of the NExt procedure consists of an optimal compression of the redundant information contained in the pixels via a mapping from pixel intensities to a subspace individualized through principal component analysis. At magnitudes fainter than the completeness limit, stars are usually almost indistinguishable from galaxies, and therefore the parameters characterizing the two classes do not lie in disconnected subspaces, thus preventing the use of unsupervised methods. We therefore adopted a supervised NN (i.e. a NN that first finds the rules to classify objects from examples and then applies them to the whole data set). In practice, each object is classified depending on its membership of the regions mapping the input feature space in the training set. In order to obtain an objective and reliable classification, instead of using an arbitrarily defined set of features we use a NN to select the most significant features among the large number of measured ones, and then we use these selected features to perform the classification task. In order to optimize the performance of the system, we implemented and tested several different models of NN. The comparison of the NExt performance with that of the best detection and classification package known to the authors (SExtractor) shows that NExt is at least as effective as the best traditional packages.

Fuzzy Group Decision Making With Incomplete Information Guided by Social Influence

A promising research area in the field of group decision making (GDM) is the study of interpersonal influence and its impact on the evolution of experts’ opinions. In conventional GDM models, a group of experts express their individual preferences on a finite set of alternatives, then preferences are aggregated and the best alternative, satisfying the majority of experts, is selected. Nevertheless, in real situations, experts form their opinions in a complex interpersonal environment where preferences are liable to change due to social influence. In order to take into account the effects of social influence during the GDM process, we propose a new influence-guided GDM model based on the following assumptions: experts influence each other and the more an expert trusts in another expert, the more his opinion is influenced by that expert. The effects of social influence are especially relevant to cases when, due to domain complexity, limited expertise or pressure to make a decision, an expert is unable to express preferences on some alternatives, i.e., in presence of incomplete information. The proposed model adopts fuzzy rankings to collect both experts’ preferences on available alternatives and trust statements on other experts. Starting from collected information, possibly incomplete, the configuration and the strengths of interpersonal influences are evaluated and represented through a social influence network (SIN). The SIN, in its turn, is used to estimate missing preferences and evolve them by simulating the effects of experts’ interpersonal influence before aggregating them for the selection of the best alternative. The proposed model has been experimented with synthetic data to demonstrate the influence driven evolution of opinions and its convergence properties.

How to integrate technology‐enhanced learning with business process management

Purpose – The purpose of this paper is to propose an innovative approach for providing an answer to the emerging trends on how to integrate e-learning efficiently in the business value chain in medium and large enterprises. Design/methodology/approach – The proposed approach defines methodologies and technologies for integrating technology-enhanced learning with knowledge and human resources management based on a synergistic use of knowledge models, methods, technologies and approaches covering different steps of the knowledge life-cycle. Findings – The proposed approach makes explicit and supports, from the methodological, technological and organizational points of view, mutual dependencies between the enterprise’s organizational learning and the business processes, considering also their integration in order to allow the optimization of employees’ learning plans with respect to business processes and taking into account competencies, skills, performances and knowledge available inside the organization. Practical implications – This mutual dependency, bridging individual and organizational learning, enables an improvement loop to become a key aspect for successful business process improvement (BPI) and business process reengineering (BPR), enabling closure of, at the same time, the learning and knowledge loops at individual, group and organization levels. Originality/value – The proposed improvements are relevant with respect to the state of the art and respond to a real need felt by enterprises and further commercial solutions and research projects on the theme.

Semantic Web Fostering Enterprise 2.0

The term Enterprise 2.0 applies to the use of Web 2.0 technologies as a support for business activities within the organizations. These technologies are exploited to foster inter-persons collaboration, information exchange and knowledge sharing, also outside the organization, to establish relationships based on conversational modalities rather than on traditional business communication. The vision of Enterprise 2.0 places a high value on the importance of social networks inside and outside the organization stimulating flexibility, adaptability and innovation between workers, managers, customers, suppliers and consultants. The integration between the Web 2.0 tools with traditional enterprise software, the aggregation of organization inner data with external data and the choice of adequate knowledge representations are critical aspects to be faced in order to further the growth of smart applications in the Enterprise 2.0 context. In this work we propose an approach, based on Semantic Web techniques, to relax the aforementioned critical issues.

Elicitation of latent learning needs through learning goals recommendation

The aim of a recommender system is to estimate the relevance of a set of objects belonging to a given domain, starting from the information available about users and objects. Adaptive e-learning systems are able to automatically generate personalized learning experiences starting from a learner profile and a set of target learning goals. Starting form research results of these fields we defined a methodology and developed a software prototype able to recommend learning goals and to generate learning experiences for learners using an adaptive e-learning system. The prototype has been integrated within IWT: an existing commercial solution for personalized e-learning and experimented in a graduate computer science course.

A personality based adaptive approach for information systems

We defined a new adaptive approach to suggest the best interaction to the users.We get the personality of the users by inferring it from the social networks.The adaptive system instantiates for each user the best process and interface.The proposed approach includes two different layers of personalization.The approach suggests the interaction process for collaborative learning. In every context where the objective is matching needs of the users with fitting answers, the high-level performance becomes a requirement able to allow systems being useful and effective. The personalization may affect different moments of computer-humans interaction routing the users to the best answers to their needs. The most part of this complex elaboration is strictly related with the needs themselves and the residual is independent from it. It is what we may face by getting personality traits of the users.In this paper, we describe an approach that is able to get the personality of the users by inferring it from the social activities they do in order to drive them to the interactive processes they should prefer. This may happens in a wide set of situations, when they are deepened in a collaborative learning experience, in an information retrieval problem, in an e-commerce process or in a general searching activity.We defined a complete model to realize an adaptive system that may interoperate with information systems and that is able to instantiate for all the users the processes and the interfaces able to give them the best feeling and to the system the highest possible performance.

Ontology-driven data acquisition: intelligent support to legal ODR systems

We describe a system for computer-assisted writing of legal documents via a question-based mechanism. This system relies upon an underlying ontological structure meant to represent the data flow from the user’s input, and a corresponding resolution algorithm, implemented within a local engine based on a LastState Next-State model, for navigating the structure and providing the user with meaningful domain-specific support and insight. This system has been successfully applied to the scenario of civil liability for motor vehicles and is part of a larger framework for self-litigation and legal support.

CADDIE and IWT: two different ontology-based approaches to Anytime, Anywhere and Anybody Learning

The Semantic Web seems to offer great opportunities for educational systems aiming to accomplish the AAAL: Anytime, Anywhere, Anybody Learning. In this scenario, two different research projects are here introduced: CADDIE (Content Automated Design & Development Integrated Editor), developed at the DIST of the University of Genoa, and IWT (Intelligent Web Teacher), developed at the DIIMA of the University of Salerno, each of them characterized by the use of ontologies and semantic technologies in order to support instructional design and personalized learning processes. The former aims to develop a learning resources and instructional paths authoring tool based on a logical and abstract annotation model, created with the goal of guaranteeing the fexibility and personalization of instructional design, the reusability of teaching materials and of the related whole knowledge structures. The latter represents an innovative e-learning solution able to support teachers and instructional designers to model educational domains knowledge, users’ competences and preferences by a semantic approach in order to create personalized and contextualized learning activities and to allow users to communicate, to cooperate, to dynamically create new content to deliver and information to share as well as enabling platform for e-learning 2.0.