Abstract
Ensemble models have been proven successful for batch recommendation algorithms, however they have not been well studied in streaming applications. Such applications typically use incremental learning, to which standard ensemble techniques are not trivially applicable. In this paper, we study the application of three variants of online gradient boosting to top-N recommendation tasks with implicit data, in a streaming data environment. Weak models are built using a simple incremental matrix factorization algorithm for implicit feedback. Our results show a significant improvement of up to 40% over the baseline standalone model. We also show that the overhead of running multiple weak models is easily manageable in stream-based applications. © 2018, Springer Nature Switzerland AG.

Abstract
Recommender systems still mainly base their reasoning on pairwise interactions or information on individual entities, like item attributes or ratings, without properly evaluating the multiple dimensions of the recommendation problem. However, in many cases, like in music, items are rarely consumed in isolation, thus users rather need a set of items, selected to work well together, serving a specific purpose, while having some cognitive properties as a whole, related to their perception of quality and satisfaction, under given circumstances. In this paper, we introduce the term of playlist concept in order to capture the implicit characteristics of joint music item selections, related to their context, scope and general perception by the users. Although playlist consumptions may be associated with contextual attributes, these may be of various types, differently influencing users' preferences, based on their character and emotional state, therefore differently reflected on their final selections. We highlight on the use of this term in HybA, our hybrid recommender system, to identify clusters of similar playlists able to capture inherit characteristics and semantic properties, not explicitly described in them. The experimental results presented, show that this conceptual clustering results in playlist continuations of improved quality, compared to using explicit contextual parameters, or the commonly used collaborative filtering technique. © 2018 The authors and IOS Press.

Abstract
Building upon the success of the first edition, we organize the second edition of the Text2Story Workshop on Narrative Extraction from Texts in conjunction with the 41 st European Conference on Information Retrieval (ECIR 2019) on April 14, 2019. Our objective is to further consolidate the efforts of the community and reflect upon the progress made since the last edition. Although the understanding of natural language has improved over the last couple of years – with research works emerging on the grounds of information extraction and text mining – the problem of constructing consistent narrative structures is yet to be solved. It is expected that the state-of-the-art has been advancing in pursuit of methods that automatically identify, interpret and relate the different elements of narratives which are often spread among different sources. In the second edition of the workshop, we foster the discussion of recent advances in the link between Information Retrieval (IR) and formal narrative representations from text. © Springer Nature Switzerland AG 2019.

Abstract

Abstract
Cardiovascular disease is the leading cause of death in the world, and its early detection is a key to improving long-term health outcomes. The auscultation of the heart is still an important method in the medical process because it is very simple and cheap. To detect possible heart anomalies at an early stage, an automatic method enabling cardiac health low-cost screening for the general population would be highly valuable. By analyzing the phonocardiogram signals, it is possible to perform cardiac diagnosis and find possible anomalies at an early-term. Therefore, the development of intelligent and automated analysis tools of the phonocardiogram is very relevant. In this work, we use simultaneously collected electrocardiograms and phonocardiograms from the Physionet Challenge database with the main objective of determining whether a phonocardiogram corresponds to a normal or abnormal physiological state. Our main contribution is the methodological combination of time domain features and frequency domain features of phonocardiogram signals to improve cardiac disease automatic classification. This novel approach is developed using both features. First, the phonocardiogram signals are segmented with an algorithm based on a logistic regression hidden semi-Markov model, which uses electrocardiogram signals as a reference. Then, two groups of features from the time and frequency domain are extracted from the phonocardiogram segments. One group is based on motifs and the other on Mel-frequency cepstral coefficients. After that, we combine these features into a two-dimensional time-frequency heat map representation. Lastly, a binary classifier is applied to both groups of features to learn a model that discriminates between normal and abnormal phonocardiogram signals. In the experiments, three classification algorithms are used: Support Vector Machines, Convolutional Neural Network, and Random Forest. The best results are achieved when both time and Mel-frequency cepstral coefficients features are considered using a Support Vector Machines with a radial kernel.

Abstract