Recent Trends in News Information Retrieval (NewsIR’16)

The First International Workshop on Recent Trends in News Information Retrieval will take place in Padua, Italy in conjunction with ECIR 2016.

Call for Papers

Mainstream media outlets are often among the most relevant, influential and powerful sources of information. This ranges from the influence that newspapers have on elections to the damage to a brand’s reputation that a negative article on a popular blog can cause.

Information Retrieval (IR) applied to news has been a popular research area for decades but it would be a mistake to assume that news search has been ‘solved’. Not only can algorithms still be improved but also there are serious gaps in the state of the art that need to be addressed.

In this workshop, we will stimulate discussion around new and powerful uses of IR applied to news sources. We invite contributions on any of the multiple IR tasks that can help solve real user problems in this area.

Topics of Interest

Relevant topics of interest for NewsIR’16 include but are not limited to:

  • Integration of traditional and social media
  • Credibility, readability and controversy
  • Bias and plurality in news
  • News recommendation
  • Temporal aspects of news
  • Event and anomaly detection
  • Diversification
  • Summarization of multiple documents
  • Information Filtering
  • User-generated content (e.g., using comments to enhance news retrieval)
  • De-duplication and clustering of news articles
  • Author identification and disambiguation
  • Evaluation
  • Data Visualization

Data challenge track

We have released a new data collection suitable for many research projects. This consists of c.​1m recent news articles from a wide range of sources. One goal of the workshop is to define shared challenges using this data, such as news recommendation, deduplication, multi­document summarization, event detection and clustering. We encourage submissions describing experiments for retrieval tasks on the dataset. This includes, but not limited to:

  • detecting and summarising events over time;
  • identifying bias in news sources to different topics and/or different entities;
  • identifying influencers in media coverage and visualising information flow;
  • sentiment analysis on media coverage.
Further details, including instructions on how to obtain the data, can be found here: http://research.signalmedia.co/newsir16/signal-dataset.html

Submission Details

We welcome submissions of technical papers (4 pages), data challenge, demos and position papers (2 pages). All papers should be formatted in the ACM SIG double-column style. Suitable LaTeX and Word templates are available from the ACM Website (link). Submissions will be peer-reviewed by at least three members of the programme committee. We plan to publish the papers as CEUR Workshop Proceedings.

Papers must be submitted electronically in printable PDF format through the Easy Chair submission page. https://easychair.org/conferences/?conf=newsir16