Publications

2017

1. Auto-encoding user ratings via knowledge graphs in recommendation scenarios Bellini, V., Anelli, V.W., Di Noia, T., and Di Sciascio, E. ACM International Conference Proceeding Series 2017

   In the last decade, driven also by the availability of an unprecedented computational power and storage capabilities in cloud environments, we assisted to the proliferation of new algorithms, methods, and approaches in two areas of artificial intelligence: knowledge representation and machine learning. On the one side, the generation of a high rate of structured data on the Web led to the creation and publication of the so-called knowledge graphs. On the other side, deep learning emerged as one of the most promising approaches in the generation and training of models that can be applied to a wide variety of application fields. More recently, autoencoders have proven their strength in various scenarios, playing a fundamental role in unsupervised learning. In this paper, we instigate how to exploit the semantic information encoded in a knowledge graph to build connections between units in a Neural Network, thus leading to a new method, SEM-AUTO, to extract and weight semantic features that can eventually be used to build a recommender system. As adding content-based side information may mitigate the cold user problems, we tested how our approach behaves in the presence of a few ratings from a user on the Movielens 1M dataset and compare results with BPRSLIM. © 2017 Association for Computing Machinery.

   Details
2. An analysis on time- & session-Aware diversification in recommender systems Anelli, V.W., Bellini, V., Di Noia, T., La Bruna, W., Tomeo, P., and Di Sciascio, E. UMAP 2017 - Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization 2017

   In modern recommender systems, diversity has been widely acknowledged as an important factor to improve user experience and, more recently, intent-Aware approaches to diversification have been proposed to provide the user with a list of recommendations covering different aspects of her behavior. In this paper, we propose and analyze the performances of two diversification methods taking into account temporal aspects of the user profile: in the first one we adopt a temporal decay function to emphasize the importance of more recent items in the user profile while in the second one we perform an evaluation based on the identification and analysis of temporal sessions. The two proposed methods have been implemented as temporal variants of the well-known xQuAD framework. In both cases, experimental results on Netflix 100M show an improvement in terms of accuracy-diversity balance. ©2017 ACM.

   Details
3. Querying DeepWeb Data Sources as Linked Data Anelli, V.W., Bellini, V., Calí, A., De Santis, G., Di Noia, T., and Di Sciascio, E. ACM International Conference Proceeding Series 2017

   The Deep Web is constituted by dynamically generated pages, usually requested through HTML forms; it is notoriously difficult to query and to search, as its pages are obviously non-indexable. Recently, Deep Web data have been made accessible through RESTful services that return information usually structured in JSON or XML format. We propose techniques to make the Deep Web available in the Linked Data Cloud, and we study algorithms for processing queries posed in a transparent way on the Linked Data, providing answers based on the underlying Deep Web sources. We present a software prototype that exposes RESTful services as Linked Data datasets thus allowing a smoother semantic integration of different structured information sources in a global data and knowledge space. © 2017 ACM.

   Details
4. On the role of time and sessions in diversifying recommendation results Anelli, V.W., Bellini, V., Di Noia, T., La Bruna, W., Tomeo, P., and Di Sciascio, E. CEUR Workshop Proceedings 2017

   Intent-Aware approaches to diversification have been proposed in the last years to provide the user with a list of recommendations covering different aspects of her behavior. In this paper, we present two diversification methods taking into account temporal aspects of the user profile: in the first one, in order to emphasize the importance of more recent items, we adopt a temporal decay function while in the second one we take into account temporal sessions. The two proposed methods have been implemented as temporal variants of the well-known xQuAD framework and tested against the Netix 100M dataset.

   Details