Domenico Ursino

Recommendation of similar users, resources and social networks in a Social Internetworking Scenario

In this paper we propose an approach to recommend to a user similar users, resources and social networks in a Social Internetworking Scenario. Our approach presents some interesting novelties with respect to the existing ones. First of all, it operates on a Social Internetworking context and not on a single social network. Moreover, it considers not only explicit relationships among users but also the implicit ones, connecting users on the basis of shared interests and behavior; the latter is derived from the analysis of user actions in the considered Social Internetworking Scenario. In addition, it considers the presence of possible semantic anomalies involving the description of available users, resources and social networks. Finally, it takes into account not only the local information regarding involved users, resources and social networks but also the global one, i.e., the information spread all over the considered Social Internetworking Scenario.

Semi-automatic, semantic discovery of properties from database schemes

An important tool for the integration of large federated database systems is a global dictionary describing all the involved schemes into an unified framework. The first step in the construction of such a dictionary is the discovery of the properties holding among objects in different schemes. This paper presents novel algorithms to discover possible synonyms, homonyms and inclusions. In addition, the paper also deals with another crucial step in the construction of a dictionary: schema integration. The approach proposed for this step exploits inter-schema properties discovered in the previous step to achieve schema integration. This approach is also concerned with producing suitable abstractions in order to structure the description of the global dictionary into a hierarchy of concepts in order to yield a more flexible, uniform view of the attached databases. The above two steps are interleaved with other steps (mainly devoted to interfacing with database administrators and to validating the discovered properties) and have been experimented with for the construction of a global dictionary for a large number of public administration database systems.

Uniform techniques for deriving similarities of objects and subschemes in heterogeneous databases

The availability of automatic tools for inferring semantics of database schemes is useful to solve several database design problems such as that of obtaining cooperative information systems or data warehouses from large sets of data sources. In this context, a main problem is to single out similarities or dissimilarities among scheme objects (interscheme properties). This paper presents graph-based techniques for a uniform derivation of interscheme properties including synonymies, homonymies, type conflicts, and subscheme similarities. These techniques are characterized by a common core: the computation of maximum weight matchings on some bipartite weighted graphs derived using a suitable metrics to measure semantic closeness of objects. The techniques have been implemented in a system prototype. Several experiments conducted with it, and (in part) accounted for in the paper, confirmed the effectiveness of our approach.

DIKE: a system supporting the semi-automatic construction of cooperative information systems from heterogeneous databases

In this paper we present DIKE, a system supporting the semi‐automatic construction of cooperative information systems from heterogeneous databases. The input of DIKE consists of the set of databases to belong to the cooperative system. First, DIKE constructs a data repository representing a structured, integrated and consistent description of the information stored in the input databases. The data repository thus constructed is then used as the core structure of a mediator‐like module supporting the user‐friendly integrated access to available data resources. The core of DIKE is the extraction and exploitation of the inter‐schema knowledge (in the form of inter‐schema properties) relative to the involved database schemas. Copyright

A query expansion and user profile enrichment approach to improve the performance of recommender systems operating on a folksonomy

In this paper we propose a query expansion and user profile enrichment approach to improve the performance of recommender systems operating on a folksonomy, storing and classifying the tags used to label a set of available resources. Our approach builds and maintains a profile for each user. When he submits a query (consisting of a set of tags) on this folksonomy to retrieve a set of resources of his interest, it automatically finds further “authoritative” tags to enrich his query and proposes them to him. All “authoritative” tags considered interesting by the user are exploited to refine his query and, along with those tags directly specified by him, are stored in his profile in such a way to enrich it. The expansion of user queries and the enrichment of user profiles allow any content-based recommender system operating on the folksonomy to retrieve and suggest a high number of resources matching with user needs and desires. Moreover, enriched user profiles can guide any collaborative filtering recommender system to proactively discover and suggest to a user many resources relevant to him, even if he has not explicitly searched for them.

Discovering links among social networks

Distinct social networks are interconnected via bridge users, who play thus a key role when crossing information is investigated in the context of Social Internetworking analysis. Unfortunately, not always users make their role of bridge explicit by specifying the so-called me edge (i.e., the edge connecting the accounts of the same user in two distinct social networks), missing thus a potentially very useful information. As a consequence, discovering missing me edges is an important problem to face in this context yet not so far investigated. In this paper, we propose a common-neighbors approach to detecting missing me edges, which returns good results in real life settings. Indeed, an experimental campaign shows both that the state-of-the-art common-neighbors approaches cannot be effectively applied to our problem and, conversely, that our approach returns precise and complete results.

Exploitation of semantic relationships and hierarchical data structures to support a user in his annotation and browsing activities in folksonomies

In this paper we present a new approach to supporting users to annotate and browse resources referred by a folksonomy. Our approach is characterized by the following novelties: (i) it proposes a probabilistic technique to quickly and accurately determine the similarity and the generalization degrees of two tags; (ii) it proposes two hierarchical structures and two related algorithms to arrange groups of semantically related tags in a hierarchy; this allows users to visualize tags of their interests according to desired semantic granularities and, then, helps them to find those tags best expressing their information needs. In this paper we first illustrate the technical characteristics of our approach; then we describe various experiments allowing its performance to be tested; finally, we compare it with other related approaches already proposed in the literature.

A unified graph-based framework for deriving nominal interscheme properties, type conflicts and object cluster similarities

The availability of automatic tools for inferring semantics from database schemes is very relevant in designing large cooperative information system applications involving many information sources. Deriving semantics from existing data sources exploits properties of objects belonging to different input schemes (interscheme properties), such as synonymies, homonymies, type conflicts, and subscheme similarities. The paper gives a contribution in this context by proposing a collection of graph based techniques for a uniform derivation of all interscheme properties. All techniques are characterized by a common core consisting of the computation of a maximum weight matching on suitable bipartite graphs. The computation of the maximum weight matching is based on a suitable metrics which is used to measure object semantic similarities. A running example is provided to illustrate the approach.

Adaptively controlling the QoS of multimedia wireless applications through "user profiling" techniques

A large amount of research is currently focusing on the issue of the adaptive control of the quality-of-service (QoS) provided to multimedia applications in heterogeneous wireless systems. In this paper, the authors aim at contributing to this issue by proposing a mechanism that exploits user profiling techniques and suitable QoS mapping functions to introduce the soft QoS idea into a wireless multimedia scenario. The research objective is a QoS control architecture, which enables the continuous convergence between the actual user preferences and expectations and the resource constraints of the underlying wireless system. The proposed architecture operates between the system and the application layer. This allows it to achieve the intended results, by means of an effective dynamic reconfiguration of the applications and the contemporary renegotiation of the wireless resources.

An XML-Based Multiagent System for Supporting Online Recruitment Services

In this paper, we propose an Extensible Markup Language (XML)-based multiagent recommender system for supporting online recruitment services. Our system is characterized by the following features: 1) it handles user profiles for personalizing the job search over the Internet; 2) it is based on the intelligent agent technology; and 3) it uses XML for guaranteeing a light, versatile, and standard mechanism for information representation, storing, and exchange. This paper discusses the basic features of the proposed system, presents the results of an experimental study we have carried out for evaluating its performance, and makes a comparison between the proposed system and other e-recruitment systems already presented in the past.