In order to understand news, dependency patterns between objects in (economic) news items have to be detected. We propose a framework which makes it possible to discover these patterns, and support the observations with statistical analysis. Based on these patterns, alerts can be generated based on emerging news. These alerts can then be used to manage (equity) portfolios. We test our framework...

Previous research has shown that young people’s voices are under- and misrepresented in the news. However, editorial mechanisms behind this outcome remain largely unexplored. Drawing from professional frame of media accountability, people present journalism with a double challenge: to avoid harm while enabling participation. In paper, we examine including/excluding news Sweden Estonia through a...

SocialNews seeks to enhance the news results returned by online news services such as Google News or Bing News by leveraging social networking information to provide more relevant results to the user. For example, Facebook profiles contain a wealth of information about the user’s interests, hobbies, personal history, and friends. We describe a system that analyzes the content in a user’s social...

We use quantitative media (blogs, and news as a comparison) data generated by a large-scale natural language processing (NLP) text analysis system to perform a comprehensive and comparative study on how company related news variables anticipates or reflects the company’s stock trading volumes and financial returns. Building on our findings, we give a sentiment-based market-neutral trading strat...

OBJECTIVE Communicating bad news about a child's illness is a difficult task commonly faced by intensive care physicians. Greater understanding of parents' scope of experiences with bad news during their child's hospitalization will help physicians communicate more effectively. Our objective is to describe parents' perceptions of their conversations with physicians regarding their child's termi...

This article has no abstract.

Aggregators rely on votes, and links to select and present subsets of the large quantity of news and opinion items generated each day. Opinion and topic diversity in the output sets can provide individual and societal benefits, but simply selecting the most popular items may not yield as much diversity as is present in the overall pool of votes and links. In this paper, we define three diversit...

Résumé : La veille en santé animale, et notamment la détection précoce d’émergences au niveau mondial d’agents pathogènes, est l’un des moyens permettant de prévenir l’introduction en France de dangers sanitaires (Paquet et al., 2006). Cet article présente une plateforme dédiée à la collecte de données (dépêches) utiles pour la veille automatique. Le recueil des dépêches s’appuie sur des requêt...