Luca Mazzola

An integrated approach to discover tag semantics

Tag-based systems have become very common for online classification thanks to their intrinsic advantages such as self-organization and rapid evolution. However, they are still affected by some issues that limit their utility, mainly due to the inherent ambiguity in the semantics of tags. Synonyms, homonyms, and polysemous words, while not harmful for the casual user, strongly affect the quality of search results and the performances of tag-based recommendation systems. In this paper we rely on the concept of tag relatedness in order to study small groups of similar tags and detect relationships between them. This approach is grounded on a model that builds upon an edge-colored multigraph of users, tags, and resources. To put our thoughts in practice, we present a modular and extensible framework of analysis for discovering synonyms, homonyms and hierarchical relationships amongst sets of tags. Some initial results of its application to the delicious database are presented, showing that such an approach could be useful to solve some of the well known problems of folksonomies.

GVIS: a facility for adaptively mashing up and representing open learner models

In this article we present an infrastructure for creating mash up and visual representations of the user profile that combine data from different sources. We explored this approach in the context of Life Long Learning, where different platforms or services are often used to support the learning process. The system is highly configurable: data sources, data aggregations, and visualizations can be configured on the fly without changing any part of the software and have an adaptive behavior based on users or systems characteristics. The visual profiles produced can have different graphical formats and can be bound to different data, automatically adapting to personal preferences, knowledge, and contexts. A first evaluation, conducted through a questionnaire, seems to be promising thanks to the perceived usefulness and the interest in the tool.

A COMPREHENSIVE E-PRESCRIBING MODEL TO ALLOW REPRESENTING, COMPARING, AND ANALYZING AVAILABLE SYSTEMS

BACKGROUND Even though ePrescribing systems are now available in many healthcare systems and have been a crucial milestone of the roadmaps towards eHealth in the last years, there is still a large heterogeneity among functionalities and performances of different systems. OBJECTIVE In this paper, we propose an updated comprehensive model for the ePrescribing process able to represent, analyze, and compare current systems and to support the design of new, more general, systems suitable also to sustain the ePrescription process in National Healthcare Systems. METHODS After a preliminary literature review, we identified six main phases of the ePrescribing process, namely Assign, Transmit, Dispense, Administer, Monitor, and Analysis Decision. Each phase produces a digital object characterized by formal properties that ensure the collection of appropriate data and information and works as input for the next one. The impact, in terms of benefits, of ePrescribing on governance, drug surveillance, and quality of care at the individual, territorial, and governmental levels are related to the formal properties of the digital objects created at the end of each phase. RESULTS AND CONCLUSIONS The model-based implementation of each phase has an impact on the quality of care, the access to care, and the effectiveness of care delivery. The model does not cover cost evaluation, but the benefits identified can be used as basis for cost-benefit or cost-effectiveness analysis of heterogeneous systems.

Exploiting tag similarities to discover synonyms and homonyms in folksonomies

Tag‐based systems are widely available, thanks to their intrinsic advantages, such as self‐organization, currency, and ease of use. Although they represent a precious source of semantic metadata, their utility is still limited. The inherent lexical ambiguities of tags strongly affect the extraction of structured knowledge and the quality of tag‐based recommendation systems. In this paper, we propose a methodology for the analysis of tag‐based systems, addressing tag synonymy and homonymy at the same time in a holistic approach: in more detail, we exploit a tripartite graph to reduce the problem of synonyms and homonyms; we apply a customized version of Tag Context Similarity to detect them, overcoming the limitations of current similarity metrics; finally, we propose the application of an overlapping clustering algorithm to detect contexts and homonymies, then evaluate its performances, and introduce a methodology for the interpretation of its results. Copyright

Supporting Learners in Adaptive Learning Environments through the Enhancement of the Student Model

This positional paper presents our research aimed at finding some possible research directions towards the enhancement of the use of open student models in the field of Technology Enhanced Learning and Adaptive Systems. Starting from the historical evolution of the learner model, we will describe some possible uses of learner models and propose some possible directions of enhancement. We will present 6 possible directions of research, and 11 dimensions on analysis. The 6 directions have been evaluated against the dimensions, and tentative ranking has been proposed. The result of this analysis will guide the work on open learner models which will be undertaken in the context of the European Union funded project GRAPPLE [1] aimed at building an infrastructure for adaptive learning systems that will adopt the strategy of opening learner models to the course learners and instructors.

Towards home healthcare informatics

The field of information technology and the Internet has developed rapidly in the last few years. The advancements affected eHealth field too, and patient-centered and consumer-centered healthcare systems have become more and more available. However, the patient/consumer interactions with his communication environment remain to investigate. We present our contributions devoted to this research field.

Towards a decision support system for hand dermatology.

The complexity of the medical diagnosis is faced by practitioners relying mainly on their experiences. This can be acquired during daily practices and on-the-job training. Given the complexity and extensiveness of the subject, supporting tools that include knowledge extracted by highly specialized practitioners can be valuable. In the present work, a Decision Support System (DSS) for hand dermatology was developed based on data coming from a Visit Report Form (VRF). Using a Bayesian approach and factors significance difference over the population average for the case, we demonstrated the potentiality of creating an enhanced VRF that include a diagnoses distribution probability based on the DSS rules applied for the specific patient situation.

Explicit tracking in the diagnostic process for hand dermatological practices

The complexity of the medical diagnostic practices is faced nowadays mainly with an extensive and long education and with on-the-job training for GPs. Despite these efforts, a big part of the diagnostic process remains implicit in the everyday practicies of skilled professionals. This project aims at an explicit tracking of this ability through the filling-in of an additional importance level for the voices in the Electronic Medical Record. The collected data leads to the extraction of rules that can empower a Decision Support System for hand dermatological practictioner with suggestios and/or diagnoses distribution probability for a specific situation.

Challenges of the e-Health curricular education in bio-medical engineering and in medicine

Curricular recommendations coming from highly respectable associations are highly useful. Nevertheless, they show fatigue in keeping the pace of any fast evolution, as in the ICT happens. So we do the attempt to disclose the emerging challenges affecting e-Health curricular education.

GVIS: An Integrating Infrastructure for Adaptively Mashing up User Data from Different Sources

In this article we present an infrastructure for creating mash up visual representations of the user profile that combines data from different sources. We explored this approach in the context of Life Long Learning, where different platforms or services are often used to support the learning process. The system is highly configurable and adaptive: data sources, data aggregations, and visualizations can be configured on the fly by the administrative user without changing any part of the software, and have an adaptive behavior based on linear combination of conditions about user or system characteristics. The visual profiles produced can assume different graphical formats and can be bound to different data, automatically adapting to personal preferences, knowledge, and contexts. We applied our infrastructure to a set of federated Learning Management Systems, retrieving information from different sources and creating some indicators of the learning activity. The software we developed provides learners with adaptive indicators of the learning state, and allows instructors to monitor the progress of their learners.