Towards a unified framework for opinion retrieval, mining and summarization

The exponential increase of subjective, user-generated content since the birth of the Social Web, has led to the necessity of developing automatic text processing systems able to extract, process and present relevant knowledge. In this paper, we tackle the Opinion Retrieval, Mining and Summarization task, by proposing a unified framework, composed of three crucial components (information retrieval, opinion mining and text summarization) that allow the retrieval, classification and summarization of subjective information. An extensive analysis is conducted, where different configurations of the framework are suggested and analyzed, in order to determine which is the best one, and under which conditions. The evaluation carried out and the results obtained show the appropriateness of the individual components, as well as the framework as a whole. By achieving an improvement over 10% compared to the state-of-the-art approaches in the context of blogs, we can conclude that subjective text can be efficiently dealt with by means of our proposed framework.

Dynamic Social and Media Content Syndication for Second Screen

Social networking apps, sites and technologies offer a wide range of opportunities for businesses and developers to exploit the vast amount of information and user-generated content produced through social networking. In addition, the notion of second screen TV usage appears more influential than ever, with viewers continuously seeking further information and deeper engagement while watching their favourite movies or TV shows. In this work, the authors present SAM, an innovative platform that combines social media, content syndication and targets second screen usage to enhance media content provisioning, renovate the interaction with end-users and enrich their experience. SAM incorporates modern technologies and novel features in the areas of content management, dynamic social media, social mining, semantic annotation and multi-device representation to facilitate an advanced business environment for broadcasters, content and metadata providers, and editors to better exploit their assets and increase their revenues.

A novel concept-level approach for ultra-concise opinion summarization

The Web 2.0 has resulted in a shift as to how users consume and interact with the information, and has introduced a wide range of new textual genres, such as reviews or microblogs, through which users communicate, exchange, and share opinions. The exploitation of all this user-generated content is of great value both for users and companies, in order to assist them in their decision-making processes. Given this context, the analysis and development of automatic methods that can help manage online information in a quicker manner are needed. Therefore, this article proposes and evaluates a novel concept-level approach for ultra-concise opinion abstractive summarization. Our approach is characterized by the integration of syntactic sentence simplification, sentence regeneration and internal concept representation into the summarization process, thus being able to generate abstractive summaries, which is one the most challenging issues for this task. In order to be able to analyze different settings for our approach, the use of the sentence regeneration module was made optional, leading to two different versions of the system (one with sentence regeneration and one without). For testing them, a corpus of 400 English texts, gathered from reviews and tweets belonging to two different domains, was used. Although both versions were shown to be reliable methods for generating this type of summaries, the results obtained indicate that the version without sentence regeneration yielded to better results, improving the results of a number of state-of-the-art systems by 9%, whereas the version with sentence regeneration proved to be more robust to noisy data.

Assessment of the Association of Health with the Liberalisation of Trade in Services under the World Trade Organisation

Background: The liberalisation of trade in services which began in 1995 under the General Agreement on Trade in Services (GATS) of the World Trade Organisation (WTO) has generated arguments for and against its potential health effects. Our goal was to explore the relationship between the liberalisation of services under the GATS and three health indicators – life expectancy (LE), under-5 mortality (U5M) and maternal mortality (MM) - since the WTO was established. Methods and Findings: This was a cross-sectional ecological study that explored the association in 2010 and 1995 between liberalisation and health (LE, U5M and MM), and between liberalisation and progress in health in the period 1995–2010, considering variables related to economic and social policies such as per capita income (GDP pc), public expenditure on health (PEH), and income inequality (Gini index). The units of observation and analysis were WTO member countries with data available for 2010 (n = 116), 1995 (n = 114) and 1995–2010 (n = 114). We conducted bivariate and multivariate linear regression analyses adjusted for GDP pc, Gini and PEH. Increased global liberalisation in services under the WTO was associated with better health in 2010 (U5M: 20.358 p,0.001; MM: 20.338 p = 0.001; LE: 0.247 p = 0.008) and in 1995, after adjusting for economic and social policy variables. For the period 1995–2010, progress in health was associated with income equality, PEH and per capita income. No association was found with global liberalisation in services. Conclusions: The favourable association in 2010 between health and liberalisation in services under the WTO seems to reflect a pre-WTO association observed in the 1995 data. However, this liberalisation did not appear as a factor associated with progress in health during 1995–2010. Income equality, health expenditure and per capita income were more powerful determinants of the health of populations.

The Tube on YouTube: TV Series, Media Strategies, and User Tactics in a Transmedia Environment

This study analyzes the traffic generated on YouTube around television series. We selected a sample of 314 short YouTube videos about 21 Spanish TV series that premiered in 2013 by Spain’s three most popular mainstream television networks (Telecinco, Antena 3, and La1). These videos, which together received more than 24 million views, were classified according to two key variables: the nature (official or nonofficial) of the YouTube channel on which they were located and the exclusivity of their content (already broadcast on TV or Web exclusive). The analysis allows us to characterize the strategies used by TV networks on YouTube and the activity of fans as well as their efforts in the construction of a transmedia narrative universe around TV series.