Search

This study uses gamification as the carrier of understanding the motivational benefits of applying the Self-Determination Theory (SDT) in social adaptive e-learning, by proposing motivational gamification strategies rooted in SDT, as well as developing and testing these strategies. Results show high perceived motivation amongst the students, and identify a high usability of the implementation, which supports the applicability of the proposed approach.\ud

Information extracted from social network services promise to improve the accuracy of recommender systems in various domains. Against this background, community detection techniques help us understand more of users’ collective behavior by clustering similar users w.r.t. their interests, preferences and activities. The purpose of this paper is to bring the novice or practitioner quickly up to date with the main outcomes and research directions in the field of social recommendation based on community detection. The research synthesis consists of a narrative review which identifies what has been written on the topic of community-based recommender system. The comprehensive search of relevant literature aims at synthesizing prior study findings by identifying approaches that follow similar paradigms and techniques. The paper is of value to those involved with recommender systems and social media.

Since the harmful consequences of the online publication of fake news have emerged clearly, many research groups worldwide have started to work on the design and creation of systems able to detect fake news and entities that share it consciously. Therefore, manifold automatic, manual, and hybrid solutions have been proposed by industry and academia. In this article, we describe a deep investigation of the features that both from an automatic and a human point of view, are more predictive for the identification of social network profiles accountable for spreading fake news in the online environment. To achieve this goal, the features of the monitored users were extracted from Twitter , such as social and personal information as well as interaction with content and other users. Subsequently, we performed (i) an offline analysis realized through the use of deep learning techniques and (ii) an online analysis that involved real users in the classification of reliable/unreliable user profiles. The experimental results, validated from a statistical point of view, show which information best enables machines and humans to detect malicious users. We hope that our research work will provide useful insights for realizing ever more effective tools to counter misinformation and those who spread it intentionally.

Nowadays, the exponential advancement of social networks is creating new application areas for recommender systems (RSs). People-to-people RSs aim to exploit user’s interests for suggesting relevant people to follow. However, traditional recommenders do not consider that people may share similar interests, but might have different feelings or opinions about them. In this paper, we propose a novel recommendation engine which relies on the identification of semantic attitudes, that is, sentiment, volume, and objectivity, extracted from user-generated content. In order to do this at large-scale on traditional social networks, we devise a three-dimensional matrix factorization, one for each attitude. Potential temporal alterations of users’ attitudes are also taken into consideration in the factorization model. Extensive offline experiments on different real world datasets, reveal the benefits of the proposed approach compared with some state-of-the-art techniques.

This paper describes a preliminary investigation of a user modeling approach, named bag-of-signals, able to take into account how user’s interests evolve over time. The basic idea underlying such an approach is to model each potential user’s interest as a signal. In order to represent and analyze such signals, we make use of the wavelet transform, a signal processing technique that offers higher performance compared to other mathematical tools for non-stationary signals. As a case study, we employ and evaluate the proposed model in a recommender system of new users to follow in social media, focusing on Twitter. A comparative analysis on real-user data with some state-of-the-art techniques - some of which considering temporal effects as well - reveals the benefits of the proposed user modeling approach for personalized recommendations.

In this paper, we present a personalized recommender system able to suggest to the target user itineraries that both meet her preferences and needs, and are sensitive to her physical and social contexts. The recommendation process takes into account different aspects: in addition to the popularity of the points of interest (POIs), inferred by considering, for instance, the number of check-ins on social networking services such as Foursquare, it also includes the user’s profile, the current context of use, and the user’s network of social ties. The system, therefore, consists of four main modules that accomplish the following tasks: (1) the construction of the user’s profile according to her interests and tastes; (2) the creation of the path graph in the user’s proximity; (3) the routing to locate the first k itineraries that match the query; (4) their ranking through a scoring function that considers the POI popularity, the user’s profile, and her physical and social context. The proposed system was evaluated on a sample of 40 real users. Experimental results showed the effectiveness of the proposed recommender.

In the last decade, social bookmarking services have gained popularity as a way of annotating and categoriz- ing a variety of different web resources. The idea behind this work is to exploit such services for enhancing traditional query expansion techniques. Specifically, the system we propose relies on three-dimensional co- occurrence matrices, where the further dimension is introduced to represent categories of terms sharing the same semantic property. Such categories, named semantic classes, are related to the folksonomy mined from social bookmarking services such as Delicious, Digg, and StumbleUpon. The paper illustrates a comparative experimental evaluation on real datasets, such as the one collected by the Open Directory Project and the TREC 2004. We also include the results of a specific disambiguation analysis aimed to evaluate the effective- ness of our approach in comparison with state-of-the-art techniques when satisfying queries characterized by polysemic and ambiguous terms.

This paper presents a text categorization system, capable of analyzing HTML/text documents collected from the Web. The system is a component of a more extensive intelligent agent for adaptive information filtering on the Web. It is based on a hybrid case-based architecture, where two multilayer perceptrons are integrated into a case-based reasoner. An empirical evaluation of the system was performed by means of a confidence interval technique. The experimental results obtained are encouraging and support the choice of a hybrid case-based approach to text categorization.

In recent years, social networks have become one of the best ways to access information. The ease with which users connect to each other and the opportunity provided by Twitter and other social tools in order to follow person activities are increasing the use of such platforms for gathering information. The amount of available digital data is the core of the new challenges we now face. Social recommender systems can suggest both relevant content and users with common social interests. Our approach relies on a signal-based model, which explicitly includes a time dimension in the representation of the user interests. Specifically, this model takes advantage of a signal processing technique, namely, the wavelet transform, for defining an efficient pattern-based similarity function among users. Experimental comparisons with other approaches show the benefits of the proposed approach.

Weak semantic techniques rely on the integration of Semantic Web techniques with social annotations and aim to embrace the strengths of both. In this article, we propose a novel weak semantic technique for query expansion. Traditional query expansion techniques are based on the computation of two-dimensional co-occurrence matrices. Our approach proposes the use of three-dimensional matrices, where the added dimension is represented by semantic classes (i.e., categories comprising all the terms that share a semantic property) related to the folksonomy extracted from social bookmarking services, such as delicious and StumbleUpon . The results of an indepth experimental evaluation performed on both artificial datasets and real users show that our approach outperforms traditional techniques, such as relevance feedback and personalized PageRank, so confirming the validity and usefulness of the categorization of the user needs and preferences in semantic classes. We also present the results of a questionnaire aimed to know the users opinion regarding the system. As one drawback of several query expansion techniques is their high computational costs, we also provide a complexity analysis of our system, in order to show its capability of operating in real time.

Most of the existing recommendation engines do not take into consideration contextual information for suggesting interesting items to users. Features such as time, location, or weather, may affect the user preferences for a particular item. In this paper, we propose two different context-aware approaches for the movie recommendation task. The first is an hybrid recommender that assesses available contextual factors related to time in order to increase the performance of traditional CF approaches. The second approach aims at identifying users in a household that submitted a given rating. This latter approach is based on machine learning techniques, namely, neural networks and majority voting classifiers. The effectiveness of both the approaches has been experimentally validated using several evaluation metrics and a large dataset.

As with the growing degree of office automation and diffuse use of electronic media, such as e-mails, written business communication is becoming a key element to promote synergies, relationships and disseminating information about products and services. Task recognition and the definition of strategies and suitable vocabularies are some of the activities that office workers deal with each time a communicative intent has to be effectively transferred and understood by a given addressee. This paper introduces a web-based intelligent training system based on the constructivism theory and self-directed learning paradigms for assisting company workers in the drafting business letters-writing task. A case-based engine suggests ad hoc rhetorical letters that users have the chance to adapt to their particular contexts and save them into user-defined case libraries.

Social networks and collaborative tagging systems are rapidly gaining popularity as primary means for sorting and sharing data: users tag their bookmarks in order to simplify information dissemination and later lookup. Social Bookmarking services are useful in two important respects: first, they can allow an individual to remember the visited URLs, and second, tags can be made by the community to guide users towards valuable content. In this paper we focus on the latter use: we present a novel approach for personalized web search using query expansion. We further extend the family of well-known co-occurence matrix technique models by using a new way of exploring social tagging services. Our approach shows its strength particularly in the case of disambiguation of word contexts. We show how to design and implement such a system in practice and conduct several experiments on a real web-dataset collected from Regione Lazio Portal1. To the best of our knowledge this is the first study centered on using social bookmarking and tagging techniques for personalization

Classical query expansion techniques can be roughly divided into two groups: the statistical approach, which consists of the selection of top-ranked terms from relevant sources based on co-occurrence values, and the semantic approach, where candidate terms are chosen based on their meaning. In this paper we present a novel approach, in which the classical cooccurrence matrix is enhanced with metadata retrieved from social bookmarking services in order to overcome its lack of semantic attributes. The implemented system, named Nereau, combines methods from the areas of Information Retrieval and Social Network Analysis: given the original query, our system performs multiple expansions and presents results divided into categories. We use a new approach to web personalization based on user collaboration sharing of information about web documents. Our evaluation results are encouraging and suggest that personalization based on social bookmarking and tagging is a useful addition to web toolset and that the subject is worth further research, in particular with regard to increasing popularity of social and collaborative services in the WWW today.

Automatic Text Categorization (TC) is a complex and useful task for many natural language applications, and is usually performed by using a set of manually classified documents, i.e. a training collection. Term-based representation of documents has found widespread use in TC. However, one of the main shortcomings of such methods is that they largely disregard lexical semantics and, as a consequence, are not sufficiently robust with respect to variations in word usage. In this paper we design, implement, and evaluate a new text classification technique. Our main idea consists in finding a series of projections of the training data by using a new, modified LSI algorithm, projecting all training instances to the low-dimensional subspace found in the previous step, and finally inducing a binary search on the projected low-dimensional data. Our conclusion is that, with all its simplicity and efficiency, our approach is comparable to SVM accuracy on classification.

Computer and network security is an extremely active and productive research area. Scientists from all over the world address the pertaining issues, using different types of models and methods. In this article we illustrate a case-based approach where the normal user-computer interaction is read like snapshots regarding a reduced number of instances of the same application, attack-free and sufficiently different from each other. The generic case representation is obtained by interpreting in numeric form the arguments and parameters of system calls deemed potentially dangerous. The similarity measure between a new input case and the ones stored in the case library is achieved through the calculation of the Earth Mover's Distance between the corresponding feature distributions, obtained by means of cluster analysis.

With the exponential growth of the available information on the World Wide Web, a traditional search engine, even if based on sophisticated document indexing algorithms, has difficulty meeting efficiency and effectiveness performance demanded by users searching for relevant information. Users surfing the Web in search of resources to satisfy their information needs have less and less time and patience to formulate queries, wait for the results and sift through them. Consequently, it is vital in many applications - for example in an e-commerce Web site or in a scientific one - for the search system to find the right information very quickly. Personalized Web environments that build models of short-term and long-term user needs based on user actions, browsed documents or past queries are playing an increasingly crucial role: they form a winning combination, able to satisfy the user better than unpersonalized search engines based on traditional Information Retrieval (IR) techniques. Several important user personalization approaches and techniques developed for the Web search domain are illustrated in this chapter, along with examples of real systems currently being used on the Internet.

In this paper, we advance a novel approach to the problem of autonomous robot navigation. The environment is a complex indoor scene with very little a priori knowledge, and the navigation task is expressed in terms of natural language directives referring to natural features of the environment itself. The system is able to analyze digital images obtained by applying a sensor fusion algorithm to ultrasonic sensor readings. Such images are classified in different categories using a case-based approach. The architecture we propose relies on fuzzy theory for the construction of digital images, and wavelet functions for their representation and analysis.

The Web has grown from a simple hypertext system for research labs to an ubiquitous information system including virtually all human knowledge, e.g., movies, images, music, documents, etc. The traditional browsing activity seems to be often inadequate to locate information satisfying the user needs. Even search engines, based on the Information Retrieval approach, with their huge indexes show many drawbacks, which force users to sift through long lists of results or reformulate queries several times. Recently, an important research activity effort has been focusing on this vast amount of machine-accessible knowledge and on how it can be exploited in order to match the user needs. The personalization and adaptation of the human-computer interaction in information seeking by means of machine learning techniques and in AI-based representations of the information help users to address the overload problem. This chapter illustrates the most important approaches proposed to personalize the access to information, in terms of gathering resources related to given topics of interest and ranking them as a function of the current user needs and activities, as well as examples of prototypes and Web systems.

This paper discusses the automatic generation of programs by adapting the construction process to the user currently interacting with the program. A class of such systems is investigated where such generation process is continuously repeated making the program design and implementation evolve according to user behaviour. By leveraging on existing technologies (software generation facilities, modelling languages, specific and general standard metamodels) an experimental proof of concept system that is able to generate itself while interacting with the user is introduced and tested. The findings are discussed and a general organization for this class of adaptive systems is briefly proposed and compared with existing literature.

A case study in adaptive information filtering systems for the Web is presented. The described system comprises two main modules, named HUMOS and WIFS. HUMOS is a user modeling system based on stereotypes. It builds and maintains long term models of individual Internet users, representing their information needs. The user model is structured as a frame containing informative words, enhanced with semantic networks. The proposed machine learning approach for the user modeling process is based on the use of an artificial neural network for stereotype assignments. WIFS is a content-based information filtering module, capable of selecting html/text documents on computer science collected from the Web according to the interests of the user. It has been created for the very purpose of the structure of the user model utilized by HUMOS. Currently, this system acts as an adaptive interface to the Web search engine ALTA VISTATM. An empirical evaluation of the system has been made in experimental settings. The experiments focused on the evaluation, by means of a non-parametric statistics approach, of the added value in terms of system performance given by the user modeling component; it also focused on the evaluation of the usability and user acceptance of the system. The results of the experiments are satisfactory and support the choice of a user model-based approach to information filtering on the Web.

We present a new method for image retrieval by shape similarity able to deal with real images with not uniform background and possible touching/occluding objects. First of all we perform a sketch-driven segmentation of the scene by means of a Deformation Tolerant version of the Generalized Hough Transform (DTGHT). Using the DTGHT we select in the image some candidate segments to be matched with the user sketch. The candidate segments are then matched with the sketch checking the consistency of the corresponding shapes. Finally, background segments are used in order to inhibit the recognition process when they cannot be perceptually separated from the object.

This work introduces an adaptive Web search system, based on a reactive agent architecture, which drew inspiration from the Ant System computational paradigm. This system aims at searching reactively and autonomously information about a particular topic, in huge hypertextual collections, such as the Web. The adaptivity allows it to be robust to environmental alterations and to user information need changes. Besides showing significant results on standard collections, this work widens further the range of intelligent search topic, towards theories and architectures of agent and multiagent systems.

This paper presents an Automated Face Recognition (AFR) system capable of providing satisfactory results even with only one training image per individual. To obtain this result an innovative architecture has been devised with the ability to integrate organically new solutios with well-established, even classic, techniques, i.e., Principal Component Analysis (PCA) and Discrete Cosine Transforms (DCT). The process of identification thereby concludes successfully even under trying circumstances; that is, even in the presence of consistent variations in the orientation, scale and expression of the face under observation. Radial Basis Function (RBF) neural networks are used as classifiers, the output of which converge into a single block thst in turn adopts a decisional strategy. Experimental results on the Face Recognition Technology (FERET) database demonstrate the validity of our approach, and invite comparison with other systems of face recognition....

This paper first describes the effort that has been done so far by researchers in artificial intelligence in the use of case-based reasoning (CBR) for the realisation of computer-based systems in clinical problem solving. Then, the approach we have chosen for building a case-based system in a specific medical domain (liver diseases) is presented, stressing the advantages of the use of CBR in medicine. CBR is a recent approach to problem solving and learning; it means using old experiences to understand and solve new problems. A new problem is solved by finding a similar past case and reusing it in the new problem situation. The aim of this work is the development of a CBR module running on an open network architecture.

In this paper we propose a complete system for automatic annotation of tennis video sequences. The method is completely automatic and computationally efficient. The court lines are detected by means of the Hough Transform while the players' positions are extracted looking for those edge pixels whose orientation is different from the lines of the court. Finally, we show some experimental results remarking the system efficiency and classification skills.

In this paper we present a case-based approach to the recognition of digital images. The architecture we propose is based on the "wavelet transform" that has been used for the representation, in the form of old cases, of images already known to the system. The paper also presents our report on a case study in the field of "mobile robots". The described system is capable of analyzing maps obtained from the sensors of a robot, and classifing them as one of the possible "objects" present in the environment in which the robot navigates. The first results we have obtained are encouraging and support the choice of the case-based approach to image recognition using the wavelet transform as a tool for image representation and analysis.

One of the distinguishing features of Intelligent Tutoring Systems (ITS), and a winning point over traditional Computer-aided Instruction (CAI) systems, is that ITSs are endowed with problem-solving capabilities in the domain to be taught. In this article, we describe the use we have made of a particular inferential mechanism, based on a context system associated with a truth maintenance system, for building an expert system in education. In particular, we present the use of such tools in the design of the expert module of SAMPLE, an ITS for teaching high school and college students how to analyze electrical circuits in alternate current in a steady condition. We stress the capability of the system of determining all the possible solutions to a given problem even if it is proposed by a student.

Each business company collects, produces and exploits for its activities and goals large amounts of information. Most of the times this knowledge makes the intellectual capital for creating value and innovation. Knowledge management (KM) systems aim at manipulating knowledge by storing and redistributing corporate information that are acquired from the organizations members. In this context, Virtual Enterprises (VE) plays a crucial role as not permanent alliances of enterprises joined together to share resources and skills in order to better respond to business opportunities. The representation and retrieval of distributed knowledge is an important feature that information systems must provide in order to obtain advantages from this kind of enterprises. PVE (Personalized Virtual Enterprise) is an ongoing research project for developing a system able to extract and let different business companies access to collective knowledge required to achieve particular shared goals. In this paper, we report the most important features of this system, especially in the context of distributed knowledge representation and retrieval.

The architecture herein advanced finds its rationale in the visual interpretation of data obtained from monitoring computers and computer networks with the objective of detecting security violations. This new outlook on the problem may offer new and unprecedented techniques for intrusion detection which take advantage of algorithmic tools drawn from the realm of image processing and computer vision. In the system we propose, the normal interaction between users and network configuration is represented in the form of snapshots that refer to a limited number of attack-free instances of different applications. Based on the representations generated in this way, a library is built which is managed according to a case-based approach. The comparison between the query snapshot and those recorded in the system database is performed by computing the Earth Mover's Distance between the corresponding feature distributions obtained through cluster analysis.