Today’s digital media ecosystem generates massive streams of news, largely in the form of individual documents (‘articles’) within which news events and narrative structures are communicated using natural language text. The increasing quantity of text documents produced by the ecosystem has presented challenges to those seeking to understand and contextualize news events and narratives over long periods of time, leading to demands for new multidimensional, multimodal and distributed representations of news events and of the narrative structures that are constructed from them. Currently, most work on cross-document temporal processing focuses on linear timelines (i.e. representations of chronologically ordered events), however not every timeline necessarily forms a good and useful storyline.

Following the success of the 1st Workshop on Computing News Storylines (CNewsStory, ACL 2015), the 2nd edition of the Workshop on Computing News Storylines (CNewsStory, EMNLP 2016) aims at further exploring, investigating and understanding the connections between events and stories in the news.

We have identified four main reasons or leading issues:

  1. Recent advances in NLP technology have made it possible to look beyond scenario-driven, atomic extraction of events from single documents and work towards extracting story structures from multiple documents, while these documents are published over time as news streams.
  2. Policy makers, NGOs, information specialists (such as journalists and librarians) and others are increasingly in need of tools that support them in finding salient information in large amounts of information to more effectively implement policies, monitor actions of “big players” in the society and check facts. Their tasks often revolve around reconstructing cases either with respect to specific entities (e.g. person or organisations) or events (e.g. hurricane Katrina).
  3. Storylines are mainly composed of events, but the properties (semantic relations, coreferential relations, script activation and perspectives) that turn a sequence of event mentions into a storyline are still to be investigated and are not self-evident.
  4. Storylines represent explanatory schemas of events that enable us to make better selections of relevant information but also projections to the future. They form a valuable potential for exploring and predicting outcomes from news data.

This multidisciplinary workshop aims at gathering researchers in NLP, AI, knowledge representation and structured journalism together with journalists, policy makers and stakeholders in the news industry to discuss how NLP technology can help to deal with the current stream of information, manage the risks of information overload, identify different sources and perspectives, and provide unitary and easily intelligible representations of the larger and long-term storylines behind news articles.