Alessandro Micarelli

• Professor (Full) at Roma Tre University

The Internet accompanies us in every moment of our lives, supporting us in many ways. Among these, it helps us when we want to choose the best services and products. So when it comes to picking a movie to watch, a restaurant to eat in, a hotel to stay in, or a product to buy, we grab our smartphone and visit one of the countless sites where users c...

Although tremendous advances have been made in recent years, many real-world problems still cannot be solved by machines alone. Hence, the integration between Human Intelligence and Artificial Intelligence (AI) is needed. However, several challenges make this integration complex. The aim of this Special Issue (SI) was to provide a large and varied...

Nowadays, Machine Learning (ML) is present in a high number of application fields. Among these, there is also automatic trading in the financial sector. The research question underlying our research activities is as follows: can ML techniques provide added value in the prediction task in domains with high volatility such as the cryptocurrency finan...

This paper describes the design and implementation of predictive models for sports betting. Specifically, we focused on exploiting Machine Learning (ML) techniques to predict football match results. To this aim, we realized an architecture that operates in two phases. First, it extracts data from the Web through scraping techniques. Then, it gives...

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 br...

In recent years, Automated Machine Learning (AutoML) has become increasingly important in Computer Science due to the valuable potential it offers. This is testified by the high number of works published in the academic field and the significant efforts made in the industrial sector. However, some problems still need to be resolved. In this paper,...

The State of the Art of the young field of Automated Machine Learning (AutoML) is held by the connectionist approach. Several techniques of such an inspiration have recently shown promising results in automatically designing neural network architectures. However, apart from back-propagation, only a few applications of other learning techniques are...

Recommender systems (RSs) represent one of the manifold applications in which Machine Learning can unfold its potential. Nowadays, most of the major online sites selling products and services provide users with RSs that can assist them in their online experience. In recent years, therefore, we have witnessed an impressive series of proposals for no...

Finding online research papers relevant to one's interests is very challenging due to the increasing number of publications. Therefore , personalized research paper recommendation has become a significant and timely research topic. Collaborative filtering is a successful recommendation approach, which exploits the ratings given to items by users as...

One of the major problems facing our cities is the disposal of the huge amount of waste produced every day. A possible solution is represented by recycling. In this article, we propose a system for automatic recognition and extraction of materials from the unsorted waste, which takes advantage of Computer Vision and Machine Learning techniques. The...

In this paper, we propose a system for extracting, storing, and analyzing the data provided by three well-known and widespread services available online. More specifically, the system can automatically collect a real-world dataset for a selected language and/or geographical region and match similar trends expressed through different keywords. Unlik...

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...

Content-based approaches to research paper recommendation are important when user feedback is sparse or not available. The task of content-based matching is challenging, mainly due to the problem of determining the semantic similarity of texts. Nowadays, there exist many sentence embedding models that learn deep semantic representations by being tr...

In this paper, we propose an approach based on the integration of a chatbot module, a location-based service, and a recommendation algorithm. This approach has been deployed for restaurant recommendation, tested on a sample of 50 real users, and compared with some state-of-the-art algorithms. The preliminary experimental results showed the benefits...

In this paper, we describe our research activities for integrating the recommendation process of nearby points of artistic and cultural interest (POIs) with related multimedia content. The recommendation engine exploits the potential offered by linked open data (LOD), by following semantic links in the LOD graph to identify movies, books, and music...

In this article, we describe a hybrid recommender system (RS) in the artistic and cultural heritage area, which takes into account the activities on social media performed by the target user and her friends, and takes advantage of linked open data (LOD) sources. Concretely, the proposed RS (1) extracts information from Facebook by analyzing content...

Recently, tagging has become a common way for users to organize and share digital content, and tag recommendation (TR) has become a very important research topic. Most of the recommendation approaches which are based on text embedding have utilized bag-of-words technique. On the other hand, proposed deep learning methods for capturing semantic mean...

This paper proposes a recommender system that exploits linked open data (LOD) to perform a social context-aware cross-domain recommendation of personalized itineraries integrated with multimedia and textual content. To this aim, the recommendation engine considers the user profile, the context of use, and the features of the points of interest (POI...

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,...

With the increasing information overload, the identification of new users really relevant to the target user becomes more and more complicated. In this paper, we propose a social recommender based on a user model that takes into account not only her interests and preferences, but also their evolution over time and actual nature. To accurately asses...

This article describes a recommender system (RS) in the cultural heritage area, which takes into account the activities on social media performed by the target user and her friends. For this purpose, the system exploits linked open data (LOD) as well. More specifically, the proposed RS (i) extracts information from social networks (e.g., Facebook)...

In this article, we propose a system able to implicitly assess a user’s expertise in a particular topic based on her publications (e.g., scientific papers) on it and available through online bibliographic databases. This task is performed through two different approaches, both of them based on a graph-based model. The first approach (content-based)...

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 opinio...

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 consi...

Classic query expansion approaches are based on the use of two-dimensional co-occurrence matrices. In this paper, we propose the adoption 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 soci...

Among the various recommender systems proposed in the literature , there is an increase in relevance and number of those that suggest users of possible interest to the target user. In this article, we propose a new algorithm for realizing user recommenders, named SCORES (Sentiment COmmunities REcommender System). This algorithm relies on the identi...

Everyday video-sharing websites such as YouTube collect large amounts of new multimedia resources. Comments left by viewers often provide valuable information to describe sentiments, opinions and tastes of users. For this reason, we propose a novel re-ranking approach that takes into consideration that information in order to provide better recomme...

This article reports our experience in developing a recom-mender system (RS) able to suggest relevant people to the target user. Such a RS relies on a user profile represented as a set of weighted concepts related to the user's interests. The weighting function, we named sentiment-volume-objectivity (SVO) function, takes into account not only the u...

The increasing popularity of social networks has encouraged a large number of significant research works on community detection and user recommendation. The idea behind this work is that taking into account users' attitudes toward their own interests can bring benefits in performing such tasks. In this paper we describe (i) a novel method to infer...

The time spent using a web browser on a wide variety of tasks such as research activities, shopping or planning holidays is relevant. Web pages visited by users contain important hints about their interests, but empirical evaluations show that almost 40-50% of the elements of the web pages can be considered irrelevant w.r.t. the user interests driv...

Focused crawling is increasingly seen as a solution to increase the freshness and coverage of local repository of documents related to specific topics by selectively traversing paths on the web. The adaptation is a peculiar feature that makes it possible to modify the search strategies according to the particular environment, its alterations and it...

Browsing sessions are rich in elements useful to build profiles of user interests, but at the same time HTML pages include noise data, such as ads and navigation menus. Moreover, pages might cover several different topics. For these reasons they are often ignored in personalized approaches. We propose a novel approach for implicitly recognizing val...

In the last decade, social bookmarking services have gained popularity as a way of annotating and categorizing 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, wher...

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...

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 pro...

Nowadays, the emerging popularity of Social Web raises new application areas for recommender systems. The aim of a social user recommendation is to suggest new friends having similar interests. In order to identify such interests, current recommender algorithms exploit social network information or the similarity of user-generated content. The rati...

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 c...

Nowadays, several location-based services (LBSs) allow their users to take advantage of information from the Web about points of interest (POIs) such as cultural events or restaurants. To the best of our knowledge, however, none of these provides information taking into account user preferences, or other elements, in addition to location, that cont...

Adaptive query expansion (QE) allows users to better define their search domain by supplementing the original query with additional terms related to their preferences and information needs. The system we present is an extension of the traditional QE techniques, which rely on the computation of two-dimensional co-occurrence matrices. Our system make...

Adaptive query expansion (QE) allows users to better de-fine their search domain by supplementing the original query with additional terms related to their preferences and infor-mation needs. The system we present is an extension of the traditional QE techniques, which rely on the computation of two-dimensional co-occurrence matrices. Our system ma...

Recommender Systems provide suggestions for items (e.g., movies or songs) to be of use to a user. They must take into account information to deliver more useful (perceived) recommendations. Current music recom-mender takes an initial input of a song and plays music with similar characteristics, or music that other users have listened to along with...

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...

Traditional desktop search paradigm often does not fit mobile contexts. Common mobile devices provide impoverished mechanisms for text entry and small screens are able to offer only a limited set of options, therefore the users are not usually able to specify their needs. On a different note, mobile technologies have become part of the everyday lif...

Hypermedia, with its combination of multimedia and non-linear organization of links among informative nodes, provides a highly interactive environment. In structured domains such as Web-based Educational Systems, the complexity of the learning domain often requires a large set of learning nodes and conceptual interrelationships that can cause sever...

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,...

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 acti...

Human immunodeficiency virus type 1 (HIV-1) isolates differ in their use of coreceptors to enter target cells. This has important implications for both viral pathogenicity and susceptibility to entry inhibitors, recently approved or under development. Predicting HIV-1 coreceptor usage on the basis of sequence information is a challenging task, due...

Hypermedia, with its combination of multimedia and non-linear organization of links among informative nodes, provides a highly interactive environment. In structured domains such as Web-based Educational Systems, the complexity of the learning domain often requires a large set of learning nodes and conceptual interrelationships that can cause sever...

In this work we present a comparing analysis of four Query Expansion (QE) techniques. Sharing the concept of term co-occurrence, we start from a simple system based on bigrams, then we moved onto a system based on term proximity through an approach known in the literature as Hyperspace Analogue to Language (HAL), and eventually developing a solutio...

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 cl...

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 pedagogi...

Personalized retrieval of documents is a research field that has been gaining interest, since it is a possible solution to the information overload problem. The ability to adapt the retrieval process to the current user needs increases the accuracy and reduces the time users spend to formulate and sift through result lists. In this chapter we show...

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 largel...

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 instance...

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 ob...

Human immunodeficiency virus type 1 (HIV-1) isolates differ in their use of coreceptors to enter target cells. This has important implications for both viral pathogenicity and susceptibility to entry inhibitors under development. Predicting HIV-1 coreceptor usage on the basis of sequence information is a challenging task due to the high variability...

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 fro...

Personalization is the ability to retrieve information content related to users' profile and facilitate their information-seeking activities. Several environments, such as the Web, take advantage of personalization techniques because of the large amount of available information. For this reason, there is a growing interest in providing automated pe...

Browsing activities are an important source of information to build profiles of the user interests and personalize the human- computer interaction during information seeking tasks. Vis- ited pages are easily collectible, e.g., from browsers' histo- ries and toolbars, or desktop search tools, and they often con- tain documents related to the current...

A very common issue of adaptive Web-Based systems is the modeling of documents. Such documents represent domain-specific information for a number of purposes. Application areas such as Information Search, Focused Crawling and Content Adaptation (among many others) benefit from several techniques and approaches to model documents effectively. For ex...

The amount of information available online is increasing exponentially. While this information is a valuable resource, its sheer volume limits its value. Many research projects and companies are exploring the use of personalized applications that manage this deluge by tailoring the information presented to individual users. These applications all n...

The large amount of available information on the Web makes it hard for users to locate resources about particular topics of interest. Traditional search tools, e.g., search engines, do not always successfully cope with this problem, that is, helping users to seek the right information. In the personalized search domain, focused crawlers are receivi...

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 perfor- mance demanded by users searching for relevant information. Users surfing the Web in search of resources to satisfy thei...

Computer-based educational systems can teach procedural expertise inexpensively yet effectively if a holistic, self-directed instructional paradigm is used. The educational system described here is an example. It teaches users who know at least the basics of a foreign language, to write effective business letters in that language. A case-based sear...

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 Ret...

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 t...

We present a computer-based system for the automatic generation and personalization of courses. The system takes trace of the student's behavior by analyzing the results of suitable on-line tests. The tests are used to infer information on both the student's knowledge about the topics of the system's domain and her/his learning preferences. Both ki...

Several statistical approaches for user proling have been proposed in order to recognize users' information needs during their interaction with information sources. Human memory processes in terms of learning and retrieval are with no doubt some of the fundamental elements that take part during this interaction, but actually only a few models for u...

The aim of the European funded project Diogene (which is going to be closed the 31st of October 2004) [Diogene] has been the construction of an automatic “brokering environment” for e-learning in a Semantic Web scenario. The Diogene platform is able to act as an intermediary between the learners and different “content providers”, specialized traini...

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 f...

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 i...

This paper presents a system developed for adaptive retrieval and the filtering of documents belonging to digital libraries available on the Web. This system, called InfoWeb, is currently in operation on the ENEA (National Entity for Alternative Energy) digital library Web site reserved to the cultural heritage and environment domain. InfoWeb recor...

In this paper we propose a vision-based system that lets the robot recognize an environment observed through the construction of a perspective structure which characterizes it. The individualization of the most significant characteristics of the perspective structure is performed by a geometric method that, using the information given by the image,...

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 reac- tively and autonomously information about a particular topic, in huge hypertextual collections, such as the Web. The adaptivity allows it to be robust to e...

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 solutions with well-established, even classic, techniques, i.e., Principal Componen...

We propose a Web tutoring system in which Artificial Intelligence techniques and Semantic Web approaches are integrated in order to provide an automatic tool able both to completely customize learning on the student's needs and to exchange learning material with other Web systems. IWT (Intelligent Web Teacher) is based on an ad hoc knowledge repres...

L’e-learning sta acquisendo importanza sempre maggiore negli ambienti didattico/formativi moderni grazie ai suoi innegabili vantaggi rispetto alla tradizionale formazione in aula. Purtroppo le piattaforme di e-learning attualmente esistenti sulla scena tendono a sfruttare la tecnologia solo come veicolo dell’esperienza formativa piuttosto che come...

A new approach to the Text Categorization problem is here presented. It is called Gaussian Weighting and it is a supervised learning algorithm that, during the training phase, estimates two very simple and easily computable statistics which are: the Presence \emphP, how much a term \emph{t} is present in a category \emph{c}; the Expressiveness \emp...

We present a new method for image retrieval by shape similarity able to deal with real images with not uniform background and possible touch­ ing/occluding objects. First of all we perform a sketch-driven segmentation of the scene by means of a Deformation Tolerant version of the General­ ized Hough Transform (DTGHT). Using the DT- G11T we select i...

Internet represents one of the most important and va riegated collection of information present in the world. With the growing utilization of such a mean, the amount of the available information has growed in an exponential way but, paradoxally, the possibilities for the users to run them profitably have reduced, a phenomenon often called informati...

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 co...

In this paper we propose a complete architecture of an automatic computer based educational system which exploits tools and methodologies taken from various Artificial Intelligence areas. We use a smart description of knowledge (concerning both the didactic domain knowledge and the student model) and inference mechanisms to achieve an efficient and...

Sommario In questo articolo viene presentato un sistema di categoriz-zazione di testi basato su un metodo di classificazione innovativo chiamato ModRadial. Tale metodo rappresenta le categorie di documenti come delle liste ordinate di RBF monodimensionali. Questa nuova metodologia si ispira alle reti RBF, soprattutto per l'attivazione delle funzion...

ei confronti del rumore e occlusioni. Inoltre la GHT non richiede l'operazione di segmentazione come accade invece per la maggior parte dei sistemi esistenti. E' bene notare che la segmentazione (intesa come separazione degli oggetti in un'immagine) e un processo molto complesso, eseguito il piu delle volte in modo non automatico. Il difetto princi...