Pierluigi Grillo

The evaluation of a social adaptive website for cultural events

In this paper, we present an evaluation of a social adaptive website in the domain of cultural events, iCITY DSA, which provides information about cultural resources and events that promote the cultural heritage in the city of Turin. Using this evaluation, our objective was to investigate the actual usage of a social adaptive website, in an effort to discover the real behavior of users, the unforeseen correlations among user actions and the consequent interactive behavior, the accuracy of both system and social recommendations and their impact on the users themselves, and the role of tagging in the user modeling process. The major contributions of the paper are manifold: insights into user interactions with social adaptive systems; guidelines for future designs; evaluation of the tagging activity and tag meanings in relation to the application domain and thus their impact on the representation of the user model; and a demonstration of how a combination and interplay of evaluation methodologies (e.g., quantitative and qualitative) can enhance our comprehension of evaluation data.

Supporting content discovery and organization in networks of contents and users

The design of approaches for supporting the user in the navigation of a variety of contents is an interesting area of research with many potential applications. In particular, interactive television (iTV) offers users the opportunity of accessing a huge amount of contents, ranging from general to specialized ones. As a consequence, the exploration of such contents must be supported in some way. In this paper, we present an innovative approach that integrates some recent methodologies and technologies developed in different areas of Artificial Intelligence and the Web: user-model-based adaptation, social networking, semantic annotation, and content sharing. We show how the integration of these technologies can provide interesting opportunities for a new approach to content navigation and discovery based on the possibility of exploring personalized networks of contents, users and concepts. Also, we focus on the specific goal of designing a platform for accessing iTV contents with the aim of providing the user with many alternative ways of exploring and discovering potentially interesting videos. After discussing the application, integrated in a project by Telecom Italia for a new paradigm of iTV, we preset the architecture we designed for integrating the methodologies discussed above.

Using mobile phone cameras to interact with ontological data

In addition to being used to access data and services on the Internet, mobile phones can also be used to retrieve information about physical objects. In this paper we present a framework and a prototype implementation of a reality browsing system that exploits mobile camera phones as access points to ontological knowledge with the corresponding physical counterparts. The use of ontologies to represent the information about the objects of the domain permits for application of reasoning and querying techniques on domain elements. Users can identify a desired product by framing its logo, obtaining further information about the object in a direct, natural and intuitive way. In addition, users can perform Web 2.0 actions on objects, contributing to the creation and development of the network of objects and users. We also provide a brief description of the implemented interface and a real world user evaluation.

Dynamic interface reconfiguration based on different ontological relations

This paper presents a framework and a prototype implementation of a system that integrates ontological knowledge base with the services for the users in mobility. Our system tries to help users navigate the domain of gastronomy, offering a possibility to explore the ontological base consisting of many concepts and relations. We present the logic and technical realization of the modules responsible for knowledge base interrogation and for presenting the obtained information to a user. We also provide a brief description of the implemented interface and user evaluation.

How scales influence user rating behaviour in recommender systems

ABSTRACT Many websites allow users to rate items and share their ratings with others, for social or personalisation purposes. In recommender systems in particular, personalised suggestions are generated by predicting ratings for items that users are unaware of, based on the ratings users provided for other items. Explicit user ratings are collected by means of graphical widgets referred to as ‘rating scales’. Each system or website normally uses a specific rating scale, in many cases differing from scales used by other systems in their granularity, visual metaphor, numbering or availability of a neutral position. While many works in the field of survey design reported on the effects of rating scales on user ratings, these, however, are normally regarded as neutral tools when it comes to recommender systems. In this paper, we challenge this view and provide new empirical information about the impact of rating scales on user ratings, presenting the results of three new studies carried out in different domains. Based on these results, we demonstrate that a static mathematical mapping is not the best method to compare ratings coming from scales with different features, and suggest when it is possible to use linear functions instead.

Interacting with a Social Web of Smart Objects for Enhancing Tourist Experiences

In this paper we introduce the idea of interaction with networks of socially intelligent objects as a way of supporting tourists and introducing them to the culture of a territory and as a way of maintaing the cultural heritage of a territory alive. We illustrate this idea with an application we designed in the field of gastronomy. Socially intelligent objects are able to maintain and aggregate knowledge about themselves and their world and are able to establish social relations with other objects and people. In this way they become hubs which allow tourists to get in touch with the world of the objects which is made of a territory, its culture and traditions, people and other objects. We support natural forms of interaction without requiring any electronic infrastructring of the objects. In particular, we designed an interaction paradigm supporting a playful enhancing experience when interacting with objects. We also support a continuum of experience in the real and virtual world.

iDYNamicTV: a social adaptive television experience

The paper presents an approach to merge Web 2.0 and adaptation with TV contents in order to enrich the user experience. We present iDYNamicTV, a social Web-based recommender system dealing with multimedia contents. iDYNamicTV is part of a larger project by Telecom Italia (DynamicTV) for enhancing user experience in TV fruition. The goal of iDynamicTV is to provide facilities to entertain when exploring and discovering media contents on the Web using a computer interface.

WantEat: interacting with social networks of smart objects for sharing cultural heritage and supporting sustainability

WantEat is about interacting with everyday objects that become intelligent hubs for accessing and sharing the cultural heritage of a territory. Objects are smart in the sense that they share knowledge with users, interact with them in a personalized way and maintain social relationships with users and other objects. When interacting with an object, a user is also introduced to the social network of its friends; the user can explore this network to discover new interesting information, services, objects, people. The objects we consider belong to the realm of gastronomy, including food items, shops, restaurants, cooks, recipes, etc. On the one hand, this allows people to get deeply in touch with the culture of a territory, making people aware of its traditions and supporting a sustainable gastronomy; on the other hand, the approach supports networking and the promotion of local quality productions and economy.