Francesco Orciuoli

Advanced ontology management system for personalised e-Learning

The use of ontologies to model the knowledge of specific domains represents a key aspect for the integration of information coming from different sources, for supporting collaboration within virtual communities, for improving information retrieval, and more generally, it is important for reasoning on available knowledge. In the e-Learning field, ontologies can be used to model educational domains and to build, organize and update specific learning resources (i.e. learning objects, learner profiles, learning paths, etc.). One of the main problems of educational domains modeling is the lacking of expertise in the knowledge engineering field by the e-Learning actors. This paper presents an integrated approach to manage the life-cycle of ontologies, used to define personalised e-Learning experiences supporting blended learning activities, without any specific expertise in knowledge engineering.

Ontology Extraction for Knowledge Reuse: The e-Learning Perspective

Ontologies have been frequently employed in order to solve problems derived from the management of shared distributed knowledge and the efficient integration of information across different applications. However, the process of ontology building is still a lengthy and error-prone task. Therefore, a number of research studies to (semi-)automatically build ontologies from existing documents have been developed. In this paper, we present our approach to extract relevant ontology concepts and their relationships from a knowledge base of heterogeneous text documents. We also show the architecture of the implemented system and discuss the experiments in a real-world context.

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.

A knowledge-based framework for emergency DSS

Emergency management requires a shared vision on everything that happens nearby the emergency zone and on the availability of resources enabling to face emergency situations. Specifically, emergency managers need to be concretely supported, by knowledge-based systems, to make critical decisions. This work introduces a framework that exploits Semantic Web technologies to harmonize heterogeneous data and soft computing methods in order to handle uncertainties and to model causal inference embedded into an emergency plan. In particular, the paper presents an approach based on Fuzzy Cognitive Maps (FCMs) to support knowledge processing and resources discovery according to the emergency features.

RSS-based e-learning recommendations exploiting fuzzy FCA for Knowledge Modeling

Nowadays, Web 2.0 focuses on user generated content, data sharing and collaboration activities. Formats like Really Simple Syndication (RSS) provide structured Web information, display changes in summary form and stay updated about news headlines of interest. This trend has also affected the e-learning domain, where RSS feeds demand for dynamic learning activities, enabling learners and teachers to access to new blog posts, to keep track of new shared media, to consult Learning Objects which meet their needs. This paper presents an approach to enrich personalized e-learning experiences with user-generated content, through a contextualized RSS-feeds fruition. The synergic exploitation of Knowledge Modeling and Formal Concept Analysis techniques enables the design and development of a system that supports learners in their learning activities by collecting, conceptualizing, classifying and providing updated information on specific topics coming from relevant information sources. An agent-based layer supervises the extraction and filtering of RSS feeds whose topics cover a specific educational domain.

Automatic generation of assessment objects and Remedial Works for MOOCs

In the MOOC environments, the students feel to be alone in the process of choosing courses leading to their learning needs and work objectives. They perceive also to be controllers of their progresses with respect to calendars, fruition, assessment results. Students come into the MOOC environments to develop or enhance professional competences, to earn formative credits and to achieve certifications to get more employment opportunities, but the statistics underline high level of drop-out and few released useful credits and final certifications. These problems are mainly related to the difficulty to guarantee the “teaching presence” in courses with thousands of learners having different background and to the ineffective assessment methods for a meaningful learning process looking at the objectives and giving feedbacks for individual learning paths construction. The work, in particular, exploits the adaptation and personalization features of IWT platform in order to provide ARWE (Adaptive Remedial Work Environment) in order to fill the lack of a one-to-one tutoring mitigating the drop-out problem in MOOCs. The main original contribution of this work concerns the definition of an approach to automatically generate quizzes, exploiting a semantic-based method, in order to populate the e-Testing tool existing in ARWE, decreasing, de facto, the effort for instructors in the assessment authoring phase.

A multi-agent fuzzy consensus model in a Situation Awareness framework

Graphical abstractDisplay Omitted In order to define systems enabling the automatic identification of occurring situations, numerous approaches employing intelligent software agents to analyse data coming from deployed sensors have been proposed. Thus, it is possible that more agents are committed to monitor the same phenomenon in the same environment. Redundancy of sensors and agents is needed, for instance, in real world applications in order to mitigate the risk of faults and threats. One of the possible side effects produced by redundancy is that agents, observing the same phenomenon, could provide discordant opinions. Indeed, solid mechanisms for reaching an agreement among these agents and produce a shared consensus on the same observations are needed. This paper proposes an approach to integrate a fuzzy-based consensus model into a Situation Awareness framework. The main idea is to consider intelligent agents as experts claiming their opinions (preferences) on a phenomenon of interest.

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.

Unfolding social content evolution along time and semantics

Abstract In the context of social media, the unstructured and dynamic nature of exchanged data and the information overload contribute to the growth of the number of research works proposing methods to improve performance of intelligent analytics services considering both time and semantics of the shared content. The presented paper focuses on the definition of a knowledge tracking framework to answer questions, such as “What is the semantic evolution of a topic (or news) along the time?”, “How did we arrive to a specific event?”, “What is the evolution of the topics of interest of a user?”, and so on. Our interest is about the elicitation of temporal patterns revealing the evolution of concepts along the time from a social media data stream; we focus on Twitter. Such patterns can be extracted at different levels of abstraction by considering different-sized time intervals and different scopes driven by the conceptualization of users’ queries. To address the proposed aim, we extend Temporal Concept Analysis and we use Description Logic to reason on semantically represented tweet streams. The evaluation activity reveals promising results from both sides quantitative and qualitative.

A framework for context-aware heterogeneous group decision making in business processes

In Business Process Management great attention is given to Computational Intelligence for supporting process life-cycle. Several approaches have been defined to support human decision making. The main drawback is that there are no solid criteria for determining optimal decisions since context, matter of discussion, and involved actors may differ at each execution. This work focuses on the definition of a framework to support and trace human decision making activities, in business processes, when heterogeneous decision-makers have to find a consensus to select most promising alternative to follow. The framework relies on Fuzzy Consensus Model and implements Reinforcement Learning algorithm to learn weight of the decision-makers through the analysis of past process executions considering context and performances of business processes. Context awareness relies on semantic web technologies enabling ontological reasoning to evaluate context similarity used to assign the right weight to the involved decision-makers also in the case when more general or more specific context occurs. The framework has been instantiated in the case study of Supply Chain Management. The analysis of the simulation results reveal that the proposed weight learning algorithm and the considered initial weight association strategies (Starting Weight and Training Executions), even if the cold start, give to decision-makers the chance to fill the gap with respect to more experienced decision makers.