1,721,012 research outputs found
Point of interest recommendation based on social and linked open data
No full textLocation-based services (LBSs) are part of our daily lives due to the huge spread of mobile devices. Such services enable us to access relevant and up-to-date information about our current surroundings at any time and everywhere. The adoption of a data-driven semantic layer coexisting with the traditional Web could help further improve LBSs, allowing them to overcome the barriers imposed by closed databases that do not take advantage of the large amount of public data available on the Internet. In this article, we propose a personalized recommender system of points of interest (POIs) located near the user’s current position, which makes use of the gold mine represented by linked open data (LOD). The target user profile is constructed and updated using two differente sources of feedback. The former is obtained by analyzing her activity on social media (i.e., Facebook). The latter is attained by inviting the user to express her interests and preferences as ratings of a sample of selected images representing specific categories of POIs. Experimental tests performed on real users allowed us to verify the good performance in terms of perceived accuracy and normalized discounted cumulative gain (NDCG). Statistical tests also enabled us to verify the significance of all the obtained results
Exploiting semantics for context-aware itinerary recommendation
No full textItinerary planning is a challenging task for users wishing to enjoy points of interest (POIs) in line with their preferences, the current context of use, and travel constraints. This article describes an approach to exploit linked open data (LOD) to perform a context-aware recommendation of personalized itineraries with related multimedia content. The recommendation process takes into account the user profile, the context of use, and the characteristics of the POIs extracted from LOD. The system, therefore, consists of six main modules that accomplish the following tasks: (i) the creation of the user profile according to her interests and preferences; (ii) the elicitation of the current context of use; (iii) the extraction and filtering of POIs from LOD through customized and dynamic queries; (iv) the itinerary construction to determine the first K itineraries that match the query; (v) their ranking through a score function that considers several factors, such as the POI popularity, the POI diversity in terms of their categories, the distance and the travel time of the itinerary, the user profile, and her physical and social context; (vi) the recommendation of multimedia and textual contents related to the itinerary suggested to the target user. The results of experimental tests performed on 50 real users show the benefits of the proposed recommender not only in terms of normalized discounted cumulative gain (nDCG), but also in terms of precision and beyond-accuracy metrics
Case-based indoor navigation
No full textThe purpose of this paper is to present a novel approach to the problem of autonomous robot navigation in a partially structured environment. The proposed solution is based on the ability of recognizing digital images that have been artificially obtained by applying a sensor fusion algorithm to ultrasonic sensor readings. Such images are classified in different categories using the well known Case-Based Reasoning (CBR) technique, as defined in the Artificial Intelligence domain. The architecture takes advantage of fuzzy theory for the construction of digital images, and wavelet functions for their analysis
A Comparative Analysis of State-of-the-Art Recommendation Techniques in the Movie Domain
No full textRecommender 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 novel recommendation techniques that claim to ensure significative improvements compared to classic techniques. In this work, we analyze some of them from a theoretical and experimental point of view and verify whether they can deliver tangible real improvements in terms of performance. Among others, we have experimented with traditional model-based and memory-based collaborative filtering, up to the most recent recommendation techniques based on deep learning. We have chosen the movie domain as an application scenario, and a version of the classic MovieLens as a dataset for training and testing our models
An Analysis of Trends and Connections in Google, Twitter, and Wikipedia
No full textIn 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. Unlike previous studies in the same area, we avoided to focus on a specific aspect and explored which resonance different topics may have between one source and another, and how quickly each source generally reacts to external events
A comparative analysis of personality-based music recommender systems
No full textThis article describes a preliminary study on considering information about the target user's personality in music recommender systems (MRSs). For this purpose, we devised and implemented four MRSs and evaluated them on a sample of real users and real-world datasets. Experimental results show that MRSs that rely on purely users' personality information are able to provide performance comparable with those of a state-of-the-art MRS, even better in terms of the diversity of the suggested items
Personalized extended government for local public administrations
No full textThis paper discusses the enterprise organization environment and reports our experience and lessons learned in developing an extension of the traditional virtual enterprise model, we named personalized extended government (PEG) model. The aim of such model is to simplify and enhance the effectiveness of e-Government services, by realizing Administration to Administration (A2A) and Administration to Citizen (A2C) processes in a personalized perspective. The features of the proposed model make it suitable for use in local public administrations. As a proof of this, it has been successfully deployed to realize the Italian Open Government Data Portal of Regione Lazio, which allows every citizen to be informed about the employment of public resources on regional territory
Special Issue on Human and Artificial Intelligence
No full textAlthough 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 collection of high-level contributions presenting novel approaches and solutions to address the above issues.
This Special Issue contains 14 papers (13 research papers and 1 review paper) that deal with various topics related to human–machine interactions and cooperation. Most of these works concern different aspects of recommender systems (RSs), which are among the most widespread decision support systems. The domains covered range from healthcare to movies and from biometrics to cultural heritage. However, there are also contributions on vocal assistants and smart interactive technologies
A signal-based approach to news recommendation
No full textIn this paper, we describe our research activity on an approach to personalized news recommendation, which captures the temporal dynamics of the active user's interests. In such recommender, the user profile explicitly involves the time dimension in representing her interests and preferences. Each user's interest is represented as a signal, thus characterizing its evolution over time. To this aim, a signal processing technique (i.e., the discrete wavelet transform) is adopted to represent and analyze such signals. Furthermore, we report the experimental results of a very preliminary comparative evaluation on an online available dataset. Such results seem encouraging, thus spurring us to continue developing our approach
- …
