- iedit
In this paper we investigate the effectiveness of Recurrent Neural Networks (RNNs) in a top-N content-based recommendation scenario. Specifically, we propose a deep architecture which adopts Long Short Term Memory (LSTM) networks to... more
In this paper we investigate the effectiveness of Recurrent Neural Networks (RNNs) in a top-N content-based recommendation scenario. Specifically, we propose a deep architecture which adopts Long Short Term Memory (LSTM) networks to jointly learn two embeddings representing the items to be recommended as well as the preferences of the user. Next, given such a representation, a logistic regression layer calculates the relevance score of each item for a specific user and we returns the top-N items as recommendations. In the experimental session we evaluated the effectiveness of our approach against several baselines: first, we compared it to other shallow models based on neural networks (as Word2Vec and Doc2Vec), next we evaluated it against state-of-the-art algorithms for collaborative filtering. In both cases, our methodology obtains a significant improvement over all the baselines, thus giving evidence of the effectiveness of deep learning techniques in content-based recommendation scenarios and paving the way for several future research directions.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this chapter, we introduce a different vision of the concept of semantics, since we will present a variety of techniques that allow to build a semantics-aware representation without the need of large corpora of textual data that are... more
In this chapter, we introduce a different vision of the concept of semantics, since we will present a variety of techniques that allow to build a semantics-aware representation without the need of large corpora of textual data that are mandatory for endogenous semantics representation methodologies.
Research Interests:
In this article we propose a hybrid recommendation framework based on classification algorithms such as Random Forests and Naive Bayes, which are fed with several heterogeneous groups of features. We split our features into two classes:... more
In this article we propose a hybrid recommendation framework based on classification algorithms such as Random Forests and Naive Bayes, which are fed with several heterogeneous groups of features. We split our features into two classes: classic features, as popularity-based, collaborative and content-based ones, and extended features gathered from the LOD cloud, as basic ones (i.e. genre of a movie or the writer of a book) and graph-based features calculated on the ground of the different topological characteristics of the tripartite representation connecting users, items and properties in the LOD cloud.
Research Interests:
T-RecS is a system which implements several computational linguistic techniques for analyzing word usage variations over time periods in a document collection. We analyzed ACM RecSys conference proceedings from the first edition held in... more
T-RecS is a system which implements several computational linguistic techniques for analyzing word usage variations over time periods in a document collection. We analyzed ACM RecSys conference proceedings from the first edition held in 2007, to the one held in 2015. The idea is to identify linguistic phenomena that reflect some interesting variations for the research community, such as a topic shift, or how the correlation between two terms changed over the time, or how the similarity between two authors evolved over time. T-RecS is a web application accessible via http://193.204.187.192/recsys/.
Research Interests:
Research Interests:
Conversational Recommender Systems are gaining more and more attention in the last years. They are characterized by the ability of establishing a multi-turn dialog with the user. Since those systems generally work in a cold-start... more
Conversational Recommender Systems are gaining more and more attention in the last years. They are characterized by the ability of establishing a multi-turn dialog with the user. Since those systems generally work in a cold-start situation, most of the conversation is devoted to the preference-elicitation step. However, in order to generate good recommendations, the user profile should be as rich as possible, which requires great user effort. In this paper, we investigate the application of Active Learning techniques for improving the preference elicitation step in a Conversational Recommender System. We compared different state-of-the-art techniques, and carried out a user study with 192 users in order to assess their effectiveness both in terms of recommendation accuracy and user effort. Results demonstrated that integrating item selection strategies based on item popularity improves the quality of the recommendations in terms of Hit Rate and nDCG, compared to a strategy based only on user-provided preferences.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Preference elicitation is a crucial step for every recommendation algorithm. Traditional interaction strategies for eliciting users’ interests and needs range from button-based interfaces, where users have to select what they like among a... more
Preference elicitation is a crucial step for every recommendation algorithm. Traditional interaction strategies for eliciting users’ interests and needs range from button-based interfaces, where users have to select what they like among a set of fixed alternatives, to more recent conversational interfaces, where users have to reply to some questions formulated by the algorithm about their preferences. However, none of these strategies either mimics the dynamics of real-world open-ended interactions, or allows users to express their needs with an adequate level of expressiveness and control. In this paper, we present a strategy that allow users to express their preferences and needs through natural language statements. In particular, our natural language preference elicitation pipeline allows users to express preferences on objective movie features (e.g., actors, directors, etc.) that are extracted from a structured knowledge base, as well as on subjective features that are collected by mining user-written movie reviews. To validate our claims, we carried out a user study in the movie domain (N = 249). The main finding of our experiment is that users tend to express their preferences by using objective features, whose usage largely overcomes that of subjective features, that are more complicated to be expressed. However, the combination of objective and subjective features often leads to better recommendations, at the cost of a slightly longer conversation. We have also identified the main challenges that arise when users talk to the virtual assistant by using subjective features, and this paves the way for future developments of our methodology.
Research Interests:
Research Interests:
In this article, we present MyrrorBot , a personal digital assistant implementing a natural language interface that allows the users to: (i) access online services, such as music, video, news, and food recommendation s, in a personalized... more
In this article, we present MyrrorBot , a personal digital assistant implementing a natural language interface that allows the users to: (i) access online services, such as music, video, news, and food recommendation s, in a personalized way, by exploiting a strategy for implicit user modeling called holistic user profiling ; (ii) query their own user models, to inspect the features encoded in their profiles and to increase their awareness of the personalization process. Basically, the system allows the users to formulate natural language requests related to their information needs. Such needs are roughly classified in two groups: quantified self-related needs (e.g., Did I sleep enough? Am I extrovert? ) and personalized access to online services (e.g., Play a song I like ). The intent recognition strategy implemented in the platform automatically identifies the intent expressed by the user and forwards the request to specific services and modules that generate an appropriate answer...
Research Interests:
Recommender Systems suggest items that are likely to be the most interesting for users, based on the feedback, i.e. ratings, they provided on items already experienced in the past. Time-aware Recommender Systems (TARS) focus on temporal... more
Recommender Systems suggest items that are likely to be the most interesting for users, based on the feedback, i.e. ratings, they provided on items already experienced in the past. Time-aware Recommender Systems (TARS) focus on temporal context of ratings in order to track the evolution of user preferences and to adapt suggestions accordingly. In fact, some people’s interests tend to persist for a long time, while others change more quickly, because they might be related to volatile information needs. In this paper, we focus on the problem of building an effective profile for short-term preferences. A simple approach is to learn the short-term model from the most recent ratings, discarding older data. It is based on the assumption that the more recent the data is, the more it contributes to find items the user will shortly be interested in. We propose an improvement of this classical model, which tracks the evolution of user interests by exploiting the content of the items, besides ...
Research Interests:
Research Interests:
In this paper we present HealthNet (HN), a social network that helps patients to meet the best doctor for her health condition. The core component of HN is a recommender system that suggests to the user patients similar to her, and... more
In this paper we present HealthNet (HN), a social network that helps patients to meet the best doctor for her health condition. The core component of HN is a recommender system that suggests to the user patients similar to her, and generates suggestions about doctors and hospitals that best match her patient profile. Currently an alpha version of HN is available only for Italian users, but in the next future we want to extend the platform to other languages. We organized three focus groups with patients, practitioners, and health organizations in order to obtain comments and suggestions. All were very enthusiastic by using the prototype version of HN.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper we present ExpLOD, a framework which exploits the information available in the Linked Open Data (LOD) cloud to generate a natural language explanation of the suggestions produced by a recommendation algorithm. The... more
In this paper we present ExpLOD, a framework which exploits the information available in the Linked Open Data (LOD) cloud to generate a natural language explanation of the suggestions produced by a recommendation algorithm. The methodology is based on building a graph in which the items liked by a user are connected to the items recommended through the properties available in the LOD cloud. Next, given this graph, we implemented some techniques to rank those properties and we used the most relevant ones to feed a module for generating explanations in natural language. In the experimental evaluation we performed a user study with 308 subjects aiming to investigate to what extent our explanation framework can lead to more transparent, trustful and engaging recommendations. The preliminary results provided us with encouraging findings, since our algorithm performed better than both a non-personalized explanation baseline and a popularity-based one.
Research Interests:
This paper presents T-RecS (Temporal analysis of Recommender Systems conference proceedings), a framework that supplies services to analyze the Recommender Systems Conference proceedings from the first edition, held in 2007, to the last... more
This paper presents T-RecS (Temporal analysis of Recommender Systems conference proceedings), a framework that supplies services to analyze the Recommender Systems Conference proceedings from the first edition, held in 2007, to the last one, held in 2015, under a temporal point of view. The idea behind T-RecS is to identify linguistic phenomena that reflect some interesting variations for the research community, such as topic drift, or how the correlation between two terms changed over time, or how similarity between two authors evolved over time.
Research Interests:
Research Interests:
Research Interests:
Abstract. This paper describes the possible use of advanced contentbased recommendation methods in the area of Digital Libraries. Contentbased recommenders analyze documents previously rated by a target user, and build a profile exploited... more
Abstract. This paper describes the possible use of advanced contentbased recommendation methods in the area of Digital Libraries. Contentbased recommenders analyze documents previously rated by a target user, and build a profile exploited to recommend new potentially interesting documents. We adopt a semantic content-based recommender called Item Recommender (ITR), which learns a user profile from documents previously processed by word sense disambiguation procedures in order to extract relevant concepts representing ...
Research Interests:
Abstract. Recommender systems are popular tools to aid users in finding interesting and relevant TV shows and other digital video assets, based on implicitly defined user preferences. In this context, a common assumption is that user... more
Abstract. Recommender systems are popular tools to aid users in finding interesting and relevant TV shows and other digital video assets, based on implicitly defined user preferences. In this context, a common assumption is that user preferences can be specified by program types (such as documentary, sports), and that an asset can be labeled by one or more program types, thus allowing an initial coarse preselection of potentially interesting assets. Furthermore each asset has a short textual description, which allows us to ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this article we introduce the concept of queryable user profile, that is to say, a representation of the user that can be queried through natural language requests. Such a representation allows the user to inspect the information that... more
In this article we introduce the concept of queryable user profile, that is to say, a representation of the user that can be queried through natural language requests. Such a representation allows the user to inspect the information that are encoded in her own profile and is supposed to: (i) make profiling and personalization processes more transparent and responsible; (ii) improve self-awareness and self-consciousness about personal data that are spread on the Web and personal devices. To this end, we designed MyrrorBot, a conversational agent that is built on top of a platform for holistic user modeling called Myrror. Basically, the system supports two groups of intents: (i) natural language requests to inspect the information encoded in the profile; (ii) personalized access to online services, such as music, video, news, and food recommendation. In both the scenarios, every question is caught by the conversational agent that interprets the information need of the user and generates an appropriate answer that fulfills the request. In the experimental evaluation, we investigated both users' acceptance of the system as well as the time required to access to the information encoded in the profile, and the results showed that our system allows to significantly improve the way people can access to personal information, thus confirming the validity of the intuition and paving the way for further development of our system.
Research Interests:
Research Interests:
Research Interests:
The Italian Public Administration (PA) relies on costly manual analyses to ensure the GDPR compliance of public documents and secure personal data. Despite recent advances in Artificial Intelligence (AI) have benefited many legal fields,... more
The Italian Public Administration (PA) relies on costly manual analyses to ensure the GDPR compliance of public documents and secure personal data. Despite recent advances in Artificial Intelligence (AI) have benefited many legal fields, the automation of workflows for data protection of public documents is still only marginally affected. The main aim of this work is to design a framework that can be effectively adopted to check whether PA documents written in Italian meet the GDPR requirements. The main outcome of our interdisciplinary research is INTREPID (art ficial i elligence for gdp complianc of ublic adm nistration ocuments), an AI-based framework that can help the Italian PA to ensure GDPR compliance of public documents. INTREPID is realized by tuning some linguistic resources for Italian language processing (i.e. SpaCy and Tint) to the GDPR intelligence. In addition, we set the foundations for a text classification methodology to recognise the public documents published by ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This chapter proposes an approach for the cooperation of abduction and induction in the context of Logic Programming. We do not take a stance on the debate on the nature of abduction and induction (see Flach and Kakas, this volume),... more
This chapter proposes an approach for the cooperation of abduction and induction in the context of Logic Programming. We do not take a stance on the debate on the nature of abduction and induction (see Flach and Kakas, this volume), rather we assume the definitions that are ...
In this paper, we present the results of an empirical evaluation investigating how recommendation algorithms are affected by popularity bias. Popularity bias makes more popular items to be recommended more frequently than less popular... more
In this paper, we present the results of an empirical evaluation investigating how recommendation algorithms are affected by popularity bias. Popularity bias makes more popular items to be recommended more frequently than less popular ones, thus it is one of the most relevant issues that limits the fairness of recommender systems. In particular, we define an experimental protocol based on two state-of-theart datasets containing users' preferences on movies and books and three different recommendation paradigms, i.e., collaborative filtering, content-based filtering and graph-based algorithms. In order to evaluate the overall fairness of the recommendations we use well-known metrics such as Catalogue Coverage, Gini Index and Group Average Popularity (ΔGAP). The goal of this paper is: (i) to provide a clear picture of how recommendation techniques are affected by popularity bias; (ii) to trigger further research in the area aimed to introduce methods to mitigate or reduce biases i...
The annual conference CLIC–it (''Italian Conference on Computational Linguistics'') is an initiative of the ''Italian Association of Computational Linguistics'' (AILC – www.ai-lc.it) which is intended to... more
The annual conference CLIC–it (''Italian Conference on Computational Linguistics'') is an initiative of the ''Italian Association of Computational Linguistics'' (AILC – www.ai-lc.it) which is intended to meet the need for a national and international forum for the promotion and dissemination of high-level original research in the field of Computational Linguistics (CL), with particular emphasis on Italian. The volume gathers the Proceedings of the ''Third Italian Conference on Computational Linguistics'' (CLiC–it 2016), held in Naples on 5-6 December 2016. The CLiC–it 2016 papers cover a wide range of topics in the area of computational linguistics and natural language (both written and spoken) processing, by targeting state–of–art theoretical results, experimental methodologies, technologies and application perspectives, and by addressing challenges, open issues and new perspectives related to current and novel trends of the discipline
Research Interests:
Paper presented at: http://www.ital-ia.it/ CINI Italian Congress on Artificial Intelligence
The general problem… Huge number of Web sites and volume of on-line data (information overloading) Users overloaded with a large amount of information Difficulty in finding relevant documents Consequence: searching may be time consuming!... more
The general problem… Huge number of Web sites and volume of on-line data (information overloading) Users overloaded with a large amount of information Difficulty in finding relevant documents Consequence: searching may be time consuming! Demand for automated user support Need for intelligent solutions able to support users in finding documents according to their interests Learning user profiles in digital libraries 2 1 …and problems in e-commerce Critical aspect in e-commerce � Millions of products for sale � Customers overloaded with a large amount of product information � Searching may be time consuming! Need for personalized solutions able to support customers in retrieving relevant products User interests useful to achieve personalization Learning user profiles in digital libraries 3