The extraordinary technological progress we have witnessed in recent years has made it possible to generate and exchange multimedia content at an unprecedented rate. As a consequence, massive collections of multimedia objects are now widely available to a large population of users. As the task of browsing such large collections could be daunting, Recommender Systems are being developed to assist users in finding items that match their needs and preferences. In this article, we present a novel approach to recommendation in multimedia browsing systems, based on modeling recommendation as a social choice problem. In social choice theory, a set of voters is called to rank a set of alternatives, and individual rankings are aggregated into a global ranking. In our formulation, the set of voters and the set of alternatives both coincide with the set of objects in the data collection. We first define what constitutes a choice in the browsing domain and then define a mechanism to aggregate individual choices into a global ranking. The result is a framework for computing customized recommendations by originally combining intrinsic features of multimedia objects, past behavior of individual users, and overall behavior of the entire community of users. Recommendations are ranked using an importance ranking algorithm that resembles the well-known PageRank strategy. Experiments conducted on a prototype of the proposed system confirm the effectiveness and efficiency of our approach.

Production of extra virgin olive oil (EVOO) represents an important element for the economy of Southern Italy. Therefore, EVOO is recognized as a food with noticeable biological effects. Our study aimed to evaluate the antimicrobial activity exhibited by the polyphenolic extracts of EVOOs, obtained from three varieties of Olea europea L. (Ruvea antica, Ravece, and Ogliarola) cultivated in the village of Montella, Avellino, Southern Italy. The study evaluated the inhibiting effect of the extracts against some Gram-positive and Gram-negative bacteria. Statistical analysis, used to relate values of antimicrobial activity to total polyphenols and phenolic composition, revealed a different behavior among the three EVOO polyphenol extracts. The method applied could be useful to predict the influence of singular metabolites on the antimicrobial activity.

Bioactive compounds of different Campania native sweet pepper varieties were evaluated. Polyphenols ranged between 1.37 mmol g⁻¹ and 3.42 mmol g⁻¹, β-carotene was abundant in the red variety “Cazzone” (7.05 μg g⁻¹). Yellow and red varieties showed a content of ascorbic acid not inferior to 0.82 mg g⁻¹, while in some green varieties the presence of ascorbic acid was almost inconsistent. Interrelationships between the parameters analyzed and the varieties showed that ascorbic acid could represent the factor mostly influencing the antioxidant activity. Polyphenol profile was different among the varieties, with a general prevalence of acidic phenols in yellow varieties and of flavonoids in red varieties. Principal Component Analysis, applied to ascorbic acid, total polyphenols and β-carotene, revealed that two of the green varieties (“Friariello napoletano” and “Friariello Sigaretta”) were well clustered and that the yellow variety “Corno di capra” showed similarity with the green varieties, in particular with “Friariello Nocerese”. This was confirmed by the interrelationships applied to polyphenol composition, which let us to light on a clustering of several red and yellow varieties, and that mainly the yellow ”Corno di capra” was closer to the green varieties of “Friariello”.

One of the most important challenge in the information access field is information overload. To cope with this problem, in this paper, we present a strategy for a semantic multimedia recommender system that computes customized recommendations using semantic contents and low-level features of multimedia objects, past behavior of individual users and behavior of the users' community as a whole. We have implemented a recommender prototype for browsing the Uffizi Gallery digital picture collection. Then, we investigated the effectiveness of the proposed approach, based on the users satisfaction. The obtained preliminary experimental results show that our approach is quite promising and encourages further research in this direction.