Search

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-39878-0_13, Proceedings of 14th International Conference, EC-Web 2013, Prague, Czech Republic, August 27-28, 2013., Context-aware recommender systems have been proven to improve the performance of recommendations in a wide array of domains and applications. Despite individual improvements, little work has been done on comparing different approaches, in order to determine which of them outperform the others, and under what circumstances. In this paper we address this issue by conducting an empirical comparison of several pre-filtering, post-filtering and contextual modeling approaches on the movie recommendation domain. To acquire confident contextual information, we performed a user study where participants were asked to rate movies, stating the time and social companion with which they preferred to watch the rated movies. The results of our evaluation show that there is neither a clear superior contextualization approach nor an always best contextual signal, and that achieved improvements depend on the recommendation algorithm used together with each contextualization approach. Nonetheless, we conclude with a number of cues and advices about which particular combinations of contextualization approaches and recommendation algorithms could be better suited for the movie recommendation domain., This work was supported by the Spanish Government (TIN2011-28538-C02) and the Regional Government of Madrid (S2009TIC-1542)

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-40643-0_5, Proceedings of 15th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2013, Madrid, Spain, September 17-20, 2013., In this paper we present a contextual modeling approach for model-based recommender systems that integrates and exploits both user preferences and contextual signals in a common vector space. Differently to previous work, we conduct a user study acquiring and analyzing a variety of realistic contextual signals associated to user preferences in several domains. Moreover, we report empirical results evaluating our approach in the movie and music domains, which show that enhancing model-based recommender systems with time, location and social companion information improves the accuracy of generated recommendations.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-40643-0_3, Proceedings of 15th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2013, Madrid, Spain, September 17-20, 2013., Online services are usually accessed via household accounts. A household account is typically shared by various users who live in the same house. This represents a problem for providing personalized services, such as recommendation. Identifying the household members who are interacting with an online system (e.g. an on-demand video service) in a given moment, is thus an interesting challenge for the recommender systems research community. Previous work has shown that methods based on the analysis of temporal patterns of users are highly accurate in the above task when they use randomly sampled test data. However, such evaluation methodology may not properly deal with the evolution of the users’ preferences and behavior through time. In this paper we evaluate several methods’ performance using time-aware evaluation methodologies. Results from our experiments show that the discrimination power of different time features varies considerably, and moreover, the accuracy achieved by the methods can be heavily penalized when using a more realistic evaluation methodology.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-39878-0_9, Proceedings of 14th International Conference, EC-Web 2013, Prague, Czech Republic, August 27-28, 2013., In this paper we present an emotion computational model based on social tags. The model is built upon an automatically generated lexicon that describes emotions by means of synonym and antonym terms, and that is linked to multiple domain-specific emotion folksonomies extracted from entertainment social tagging systems. Using these cross-domain folksonomies, we develop a number of methods that automatically transform tag-based item profiles into emotion-oriented item profiles. To validate our model we report results from a user study that show a high precision of our methods to infer the emotions evoked by items in the movie and music domains, and results from an offline evaluation that show accuracy improvements on model-based recommender systems that incorporate the extracted item emotional information., This work was supported by the Spanish Government (TIN2011-28538-C02) and the Regional Government of Madrid (S2009TIC-1542).

Proceedings of 21th International Conference, UMAP 2013, Rome, Italy, June 10-14, 2013, The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-38844-6_30, We present an emotion model based on social tags, which is built upon an automatically generated lexicon that describes emotions by means of synonym and antonym terms. Using this model we develop a number of methods that transform social tag-based item profiles into emotion-oriented item profiles. We show that the model’s representation of a number of basic emotions is in accordance with the well known psychological circumplex model of affect, and we report results from a user study that show a high precision of our methods to infer the emotions evoked by items in the movie and music domains., This work was supported by the Spanish Government (TIN2011-28538-C02) and the Regional Government of Madrid (S2009TIC-1542).

An increasingly important type of recommender systems comprises those that generate suggestions for groups rather than for individuals. In this chapter, we revise state of the art approaches on group formation, modelling and recommendation, and present challenging problems to be included in the group recommender system research agenda in the context of the Social Web.

Proceedigns of 12th International Conference, EC-Web 2011, Toulouse, France, August 30 - September 1, 2011., The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-23014-1_9, We present an approach that efficiently identifies the semantic meanings and contexts of social tags within a particular folksonomy, and exploits them to build contextualised tag-based user and item profiles. We apply our approach to a dataset obtained from Delicious social bookmarking system, and evaluate it through two experiments: a user study consisting of manual judgements of tag disambiguation and contextualisation cases, and an offline study measuring the performance of several tag-powered item recommendation algorithms by using contextualised profiles. The results obtained show that our approach is able to accurately determine the actual semantic meanings and contexts of tag annotations, and allow item recommenders to achieve better precision and recall on their predictions., This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02), and the Community of Madrid (CCG10- UAM/TIC-5877)

Proceedings of Third International Conference, ICTIR 2011, Bertinoro, Italy, September 12-14, 2011., The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-23318-0_5, Performance prediction is an appealing problem in Recommender Systems, as it enables an array of strategies for deciding when to deliver or hold back recommendations based on their foreseen accuracy. The problem, however, has been barely addressed explicitly in the area. In this paper, we propose adaptations of query clarity techniques from ad-hoc Information Retrieval to define performance predictors in the context of Recommender Systems, which we refer to as user clarity. Our experiments show positive results with different user clarity models in terms of the correlation with single recommender’s performance. Empiric results show significant dependency between this correlation and the recommendation method at hand, as well as competitive results in terms of average correlation., This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02), University Autónoma de Madrid and the Community of Madrid (CCG10-UAM/TIC-5877)

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-16020-2_42, Proceedings of 5th European Conference on Technology Enhanced Learning, EC-TEL 2010, Barcelona, Spain, September 28 - October 1, 2010., We present an e-learning system based on online forms that allows teachers to easily organise competitions in a classroom. This system is used in a preliminary study to evaluate whether cooperative competition is positive or not in education, and to identify which are the characteristics this kind of activity should have to be no harmful for students, motivating and helping them in their learning process., This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02), and the Community of Madrid (S2009TIC- 1542).

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-12275-0_37, Proceedings of 32nd European Conference on IR Research, ECIR 2010, Milton Keynes, UK, March 28-31, 2010., Web search personalization aims to adapt search results to a user based on his tastes, interests and needs. The way in which such personal preferences are captured, modeled and exploited distinguishes the different personalization strategies. In this paper, we propose to represent a user profile in terms of social tags, manually provided by users in folksonomy systems to describe, categorize and organize items of interest, and investigate a number of novel techniques that exploit the users’ social tags to re-rank results obtained with a Web search engine. An evaluation conducted with a dataset from Delicious social bookmarking system shows that our personalization techniques clearly outperform state of the art approaches., This research was supported by the European Commission under contract FP6-027122-SALERO and by the Spanish Ministry of Science and Education (TIN2008-06566-C04-02)

Recommender systems suggest users information items they may be interested in. User profiles or usage data are compared with some reference characteristics, which may belong to the items (content-based approach), or to other users in the same context (collaborative filtering approach). These items are usually presented as a ranking, where the more relevant an item is predicted to be for a user, the higher it appears in the ranking. In this scenario, a preferential order has to be inferred, and therefore, preference learning methods can be naturally helpful. The relevant recommendation model features for the learning-based enhancements explored in this work comprise parameters of the recommendation algorithms, and user-related attributes. In the researched approach, machine learning techniques are used to discover which model features are relevant in providing accurate recommendations. The assessment of relevant model features, which is the focus of this paper, is envisioned as the first step in a learning cycle in which improved recommendation models are produced and executed after the discovery step, based on the findings that result from it.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-04957-6_54, Proceedings of Second European Semantic Web Conference, ESWC 2005, Heraklion, Crete, Greece, May 29–June 1, 2005., Semantic search has been one of the motivations of the Semantic Web since it was envisioned. We propose a model for the exploitation of ontology-based KBs to improve search over large document repositories. Our approach includes an ontology-based scheme for the semi-automatic annotation of documents, and a retrieval system. The retrieval model is based on an adaptation of the classic vector-space model, including an annotation weighting algorithm, and a ranking algorithm. Semantic search is combined with keyword-based search to achieve tolerance to KB incompleteness. Our proposal is illustrated with sample experiments showing improvements with respect to keyword-based search, and providing ground for further research and discussion., This research was supported by the European Commission under contract FP6-027122-SALERO. The expressed content is the view of the authors but not necessarily the view of the SALERO project as a whole.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-540-88564-1_40, Proceedings of 7th International Semantic Web Conference, ISWC 2008, Karlsruhe, Germany, October 26-30, 2008., The continued increase in Web usage, in particular participation in folksonomies, reveals a trend towards a more dynamic and interactive Web where individuals can organise and share resources. Tagging has emerged as the de-facto standard for the organisation of such resources, providing a versatile and reactive knowledge management mechanism that users find easy to use and understand. It is common nowadays for users to have multiple profiles in various folksonomies, thus distributing their tagging activities. In this paper, we present a method for the automatic consolidation of user profiles across two popular social networking sites, and subsequent semantic modelling of their interests utilising Wikipedia as a multi-domain model. We evaluate how much can be learned from such sites, and in which domains the knowledge acquired is focussed. Results show that far richer interest profiles can be generated for users when multiple tag-clouds are combined., This research has been supported by the TAGora project funded by the Future and Emerging Technologies program (IST-FET) of the European Commission under the contract IST-34721. The information provided is the sole responsibility of the authors and does not reflect the Commission’s opinion. The Commission is not responsible for any use that may be made of data appearing in this publication

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-540-70987-9_34, Proceedings of 5th International Conference, AH 2008, Hannover, Germany, July 29 - August 1, 2008., We present News@hand, a news recommender system which applies semantic-based technologies to describe and relate news contents and user preferences in order to produce enhanced recommendations. The exploitation of conceptual information describing contents and user profiles, along with the capability of inferring knowledge from the semantic relations defined in the ontologies, enabling different content-based collaborative recommendation models, are the key distinctive aspects of the system. The multi-domain portability, the multi-media source applicability, and addressing of some limitations of current recommender systems are the main benefits of our proposed approach., This research was supported by the European Commission (FP6-027685-MESH) and the Spanish Ministry of Science and Education (TIN2005-06885). The expressed content is the view of the authors but not necessarily the view of the MESH project as a whole

Proceedings of 15th International Conference, EKAW 2006, Poděbrady, Czech Republic, October 2-6, 2006., The final publication is available at Springer via http://dx.doi.org/10.1007/11891451_30, We propose a multilayered semantic social network model that offers different views of common interests underlying a community of people. The applicability of the proposed model to a collaborative filtering system is empirically studied. Starting from a number of ontology-based user profiles and taking into account their common preferences, we automatically cluster the domain concept space. With the obtained semantic clusters, similarities among individuals are identified at multiple semantic preference layers, and emergent, layered social networks are defined, suitable to be used in collaborative environments and content recommenders., The research leading to this document has received funding from the European Community's Sixth Framework Programme (FP6-027685 – MESH), and the Spanish Ministry of Science and Education (TIN2005-06885). However, it reflects only the authors' views, and the European Community is not liable for any use that may be made of the information contained therein.

The analysis of investment funds information requires the availability of homogeneous information of the funds considered, which is usually generated and provisioned by different parties and in different formats. In this context, the gathering and integration of information from disparate, heterogeneous sources becomes a key task that can be considerably eased by the availability of explicit and shared information models. Furthermore, the analysis process leads to the generation of added-value information, whose consumption by other parties can also benefit from the existence of agreed information models. In this paper, we present our work on building explicit information models for investment funds in the Spanish market. An XBRL taxonomy of funds, and a translation process of XBRL taxonomies into OWL ontologies that has been applied to this taxonomy in order to obtain an OWL ontology of funds, are presented. The relative benefits of using OWL ontologies or XBRL taxonomies for the exchange and analysis of investment funds information are also discussed.

The final publication is available at Springer via http://dx.doi.org/10.1007/11494669_26, Proceedings of 8th International Work-Conference on Artificial Neural Networks, IWANN 2005, Vilanova i la Geltrú, Barcelona, Spain, June 8-10, 2005., Boosting constructs a weighted classifier out of possibly weak learners by successively concentrating on those patterns harder to classify. While giving excellent results in many problems, its performance can deteriorate in the presence of patterns with incorrect labels. In this work we shall use parallel perceptrons (PP), a novel approach to the classical committee machines, to detect whether a pattern’s label may not be correct and also whether it is redundant in the sense of being well represented in the training sample by many other similar patterns. Among other things, PP allow to naturally define margins for hidden unit activations, that we shall use to define the above pattern types. This pattern type classification allows a more nuanced approach to boosting. In particular, the procedure we shall propose, balanced boosting, uses it to modify boosting distribution updates. As we shall illustrate numerically, balanced boosting gives very good results on relatively hard classification problems, particularly in some that present a marked imbalance between class sizes., With partial support of Spain’s CICyT, TIC 01–572.

The final publication is available at Springer via http://dx.doi.org/10.1007/11499305_60, Proceedings of First International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2005, Las Palmas, Canary Islands, Spain, June 15-18, 2005, Boosting combines an ensemble of weak learners to construct a new weighted classifier that is often more accurate than any of its components. The construction of such learners, whose training sets depend on the performance of the previous members of the ensemble, is carried out by successively focusing on those patterns harder to classify. This fact deteriorates boosting’s results when dealing with malicious noise as, for instance, mislabeled training examples. In order to detect and avoid those noisy examples during the learning process, we propose the use of Parallel Perceptrons. Among other things, these novel machines allow to naturally define margins for hidden unit activations. We shall use these margins to detect which patterns may have an incorrect label and also which are safe, in the sense of being well represented in the training sample by many other similar patterns. As candidates for being noisy examples we shall reduce the weights of the former ones, and as a support for the overall detection procedure we shall augment the weights of the latter ones., With partial support of Spain’s CICyT, TIC 01–572, TIN 2004–07676

Proceedings of 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-33266-1_70, In this work we will apply Diffusion Maps (DM), a recent technique for dimensionality reduction and clustering, to build local models for wind energy forecasting. We will compare ridge regression models for K–means clusters obtained over DM features, against the models obtained for clusters constructed over the original meteorological data or principal components, and also against a global model. We will see that a combination of the DM model for the low wind power region and the global model elsewhere outperforms other options., With partial support of Spain’s CICyT, projects TIC 01–572, TIN2004–07676.

The final publication is available at Springer via http://dx.doi.org/10.1007/11492542_6, Proceedings of Second Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Part II, A natural way to deal with training samples in imbalanced class problems is to prune them removing redundant patterns, easy to classify and probably over represented, and label noisy patterns that belonging to one class are labelled as members of another. This allows classifier construction to focus on borderline patterns, likely to be the most informative ones. To appropriately define the above subsets, in this work we will use as base classifiers the so–called parallel perceptrons, a novel approach to committee machine training that allows, among other things, to naturally define margins for hidden unit activations. We shall use these margins to define the above pattern types and to iteratively perform subsample selections in an initial training set that enhance classification accuracy and allow for a balanced classifier performance even when class sizes are greatly different., With partial support of Spain’s CICyT, TIC 01–572, TIN2004–07676