Mental health problems represent a major public health challenge. Automated analysis of text related to mental health is aimed to help medical decision-making, public health policies and to improve health care. Such analysis may involve text classification. Traditionally, automated classification has been performed mainly using machine learning methods involving costly feature engineering. Recently, the performance of those methods has been dramatically improved by neural methods. However, mainly Convolutional neural networks (CNNs) have been explored. In this paper, we apply a hierarchical Recurrent neural network (RNN) architecture with an attention mechanism on social media data related to mental health. We show that this architecture improves overall classification results as compared to previously reported results on the same data. Benefitting from the attention mechanism, it can also efficiently select text elements crucial for classification decisions, which can also be used for in-depth analysis.

Abstract. This paper presents a quantitative study on the use of Topolor -a prototype that introduces Web 2.0 tools and Facebook-like appearance into an adaptive educational hypermedia system. We present the system design and its evaluation using system usability scale questionnaire and learning behavior data analysis. The results indicate high level of student satisfaction with the learning experience and the diversity of learning activities.

CoPe_it! is an innovative Web-based tool that complies with collaborative practices to provide members of communities with the appropriate means to manage individual and collective knowledge during a sense-making and/or decision-making session. In this article, we demonstrate its applicability in tackling cognitively-complex collaboration settings, which are characterized by big volumes of interrelated data obtained from diverse sources and knowledge expressed by diverse participants. We focus on issues related to the representation of such settings and propose an approach to make it easier for participants to follow the evolution of collaboration, comprehend it in its entirety, and meaningfully aggregate data to resolve the issue under consideration.

Abstract. Data extraction from the web is notoriously hard. Of the types of resources available on the web, weblogs are becoming increasingly important due to the continued growth of the blogosphere, but remain poorly explored. Past approaches to data extraction from weblogs have often involved manual intervention and suffer from low scalability. This paper proposes a fully automated information extraction methodology based on the use of web feeds and processing of HTML. The approach includes a model for generating a wrapper that exploits web feeds for deriving a set of extraction rules automatically. Instead of performing a pairwise comparison between posts, the model matches the values of the web feeds against their corresponding HTML elements retrieved from multiple weblog posts. It adopts a probabilistic approach for deriving a set of rules and automating the process of wrapper generation. An evaluation of the model is conducted on a dataset of 2,393 posts and the results (92% accuracy) show that the proposed technique enables robust extraction of weblog properties and can be applied across the blogosphere for applications such as improved information retrieval and more robust web preservation initiatives.