Leo Iaquinta

Introducing Serendipity in a Content-Based Recommender System

Today recommenders are commonly used with various purposes, especially dealing with e-commerce and information filtering tools. Content-based recommenders rely on the concept of similarity between the bought/ searched/ visited item and all the items stored in a repository. It is a common belief that the user is interested in what is similar to what she has already bought/searched/visited. We believe that there are some contexts in which this assumption is wrong: it is the case of acquiring unsearched but still useful items or pieces of information. This is called serendipity. Our purpose is to stimulate users and facilitate these serendipitous encounters to happen. This paper presents the design and implementation of a hybrid recommender system that joins a content-based approach and serendipitous heuristics in order to mitigate the over-specialization problem with surprising suggestions.

Learning Preference Models in Recommender Systems

As proved by the continuous growth of the number of web sites which embody recommender systems as a way of personalizing the experience of users with their content, recommender systems represent one of the most popular applications of principles and techniques coming from Information Filtering (IF). As IF techniques usually perform a progressive removal of nonrelevant content according to the information stored in a user profile, recommendation algorithms process information about user interests – acquired in an explicit (e.g., letting users express their opinion about items) or implicit (e.g., studying some behavioral features) way – and exploit these data to generate a list of recommended items. Although each type of filtering method has its own weaknesses and strengths, preference handling is one of the core issues in the design of every recommender system: since these systems aim to guide users in a personalized way to interesting or useful objects in a large space of possible options, it is important for them to accurately capture and model user preferences. The goal of this chapter is to provide a general overview of the approaches to learning preference models in the context of recommender systems. In the first part, we introduce general concepts and terminology of recommender systems, giving a brief analysis of advantages and drawbacks for each filtering approach. Then we will deal with the issue of learning preference models, show the most popular techniques for profile learning and preference elicitation, and analyze methods for feedback gathering in recommender systems.

Concept-based item representations for a cross-lingual content-based recommendation process

The growth of the Web is the most influential factor that contributes to the increasing importance of text retrieval and filtering systems. On one hand, the Web is becoming more and more multilingual, and on the other hand users themselves are becoming increasingly polyglot. In this context, platforms for intelligent information access as search engines or recommender systems need to evolve to deal with this increasing amount of multilingual information. This paper proposes a content-based recommender system able to generate cross-lingual recommendations. The idea is to exploit user preferences learned in a given language, to suggest item in another language. The main intuition behind the work is that, differently from keywords which are inherently language dependent, concepts are stable across different languages, allowing to deal with multilingual and cross-lingual scenarios. We propose four knowledge-based strategies to build concept-based representation of items, by relying on the knowledge contained in two knowledge sources, i.e. Wikipedia and BabelNet. We learn user profiles by leveraging the different concept-based representations, in order to define a cross-lingual recommendation process. The empirical evaluation carried out on two state of the art datasets, DBbook and Movielens, shows that concept-based approaches are suitable to provide cross-lingual recommendations, even though there is not a clear advantage of using one of the different proposed representations. However, it emerges that most of the times the approaches based on BabelNet outperform those based on Wikipedia, which clearly shows the advantage of using a native multilingual knowledge source.

Can a Recommender System Induce Serendipitous Encounters

Today recommenders are commonly used with various purposes, especially dealing with ecommerce and information filtering tools. Content-based recommenders rely on the concept of similarity between the bought/searched/visited item and all the items stored in a repository. It is a common belief that the user is interested in what is similar to what she has already bought/searched/visited. We believe that there are some contexts in which this assumption is wrong: it is the case of acquiring unsearched but still useful items or pieces of information. This is called serendipity. Our purpose is to stimulate users and facilitate these serendipitous encounters to happen. This chapter presents the design and implementation of a hybrid recommender system that joins a content-based approach and serendipitous heuristics in order to mitigate the overspecialization problem with surprising suggestions. The chapter is organized as follows: Section 2 presents background and motivation; Section 3 introduces the serendipity issue for information seeking; Section 4 covers strategies to provide serendipitous recommendations; Section 5 provides a description of our recommender system and how it discovers potentially serendipitous items in addition to content-based suggested ones; Section 6 provides the description of the experimental session carried out to evaluate the proposed ideas; finally, Section 7 draws conclusions and provides directions for future work.

The contribution of AI to enhance understanding of Cultural Heritage

The Artificial Intelligence & Cultural Heritage (AI & CH) working group was born in 1999 with the aim at promoting various scientific activities to increase a more active collaboration between the sectors of cultural assets and artificial intelligence. The many events (workshops and schools) organized over the years have shown the validity of this group for exchanging ideas and gathering researchers and practitioners from different fields. New applications of informatics and artificial intelligence have provided the opportunity to produce innovative tools for documenting, managing and communicating cultural heritage. For this anniversary we intend to show how some of the most important methods and techniques of artificial intelligence developed in this area, still represent significant tools for preservation, archiving and fruition of cultural heritage. In the following the contributions of Italian researchers involved for several years in projects related to cultural heritage, will be presented.

Recommendations toward Serendipitous Diversions

Recommenders systems are used with various purposes, especially dealing with e-commerce and information filtering tools. Content-based ones recommend items similar to those a given user has liked in the past. Indeed, the past behavior is supposed to be a reliable indicator of her future behavior. This assumption, however, causes the overspecialization problem. Our purpose is to mitigate the problem stimulating users and facilitating the serendipitous encounters to happen. This paper presents the design and implementation of a hybrid recommender system that joins a content-based approach and a serendipitous heuristic in order to provide also surprising suggestions. The reference scenario concerns with personalized tours in a museum and serendipitous items are introduced by slight diversions on the context-aware tours.

SpIteR: A Module for Recommending Dynamic Personalized Museum Tours

Recommender systems (RSs) proved to make easier the task of accessing relevant information in a broad range of domains. In content-based RSs, preferences on content items expressed by users turned out to be reliable indicators to suggest and filter interesting contents. Item representation plays a key role in content-based RSs, thus choosing proper facets to represent items is a fundamental task for deploying effective RSs. Contextual facets are often marginally relevant to predict user preferences, but in some domains disregarding contextual facets makes recommendations useless. This paper proposes a strategy to improve the effectiveness of a content-based RS that dynamically suggests tours within a museum by exploiting contextual facets such the physical layout of items and the interaction of users with the environment.

Lexical and Semantic Resources for NLP: From Words to Meanings

A user expresses her information need through words with a precise meaning, but from the machine point of view this meaning does not come with the word. A further step is needful to automatically associate it to the words. Techniques that process human language are required and also linguistic and semantic knowledge, stored within distinct and heterogeneous resources, which play an important role during all Natural Language Processing (NLP) steps. Resources management is a challenging problem, together with the correct association between URIs coming from the resources and meanings of the words. This work presents a service that, given a lexeme (an abstract unit of morphological analysis in linguistics, which roughly corresponds to a set of words that are different forms of the same word), returns all syntactic and semantic information collected from a list of lexical and semantic resources. The proposed strategy consists in merging data with origin from stable resources, such as WordNet, with data collected dynamically from evolving sources, such as the Web or Wikipedia. That strategy is implemented in a wrapper to a set of popular linguistic resources that provides a single point of access to them, in a transparent way to the user, to accomplish the computational linguistic problem of getting a rich set of linguistic and semantic annotations in a compact way.

Cluster analysis for user segmentation in e-government service domain

E-government (e-Gov) is becoming more attentive towards providing personalised services to citizens so that they can benefit from better services with less time and effort. To develop user-centred services, a crucial activity is represented by user segmentation that consists in mining needs and preferences of users by identifying homogeneous groups of users, also known as user segments, sharing similar characteristics. This work provides a comprehensive analysis of studies focusing on user segmentation. Moreover, it proposes an approach based on cluster analysis for deriving and characterising segments of users experiencing services in the e-Gov domain. Examples of application of the proposed approach on two real-world case studies are described in order to show its suitability in deriving useful user segments.