at KDD 2014, New York, United States, August 24, 2014
We have 12 accepted papers, check the full list below.
News publishing is a domain with a lot of specifics related to data processing
spanning interdisciplinary across many fields of data related research. The
aim of this workshop is to cover data analytic/mining research, approaches and
solutions for numerous data challenges related to news publishing. The key
categories of data analytic challenges in news publishing include areas like:
editorial support (media monitoring, data journalism, news bias),
content management (search, ranking, semantics),
user management (user profiling, recommendation, social media),
The workshop will be structured as a set of sections including: what news publishers’
R&Ds are doing, live system demos, contributed short papers, invited talks, and the panel.
The workshop will be video-recorded and published on videolectures.net.
Target audience will be data researchers and professionals from publishing industry
(being extensively present in New York). Some of the categories include:
Data scientists from publishing houses of all types
Journalists, editors and bloggers operating in online publishing
Data Journalists and Info-graphics creators
Software engineers from publishing houses or vendor companies
Researchers and students in social sciences related to news domain
Broader public interested in advances in data analytics for news publishing
Submission Date: June 24, 2014
Notification of Acceptance: July 8, 2014
Workshop date: Sunday, August 24, 2014
Camera-ready: Friday, Augist 1, 2014
Andraž Hribernik, Lorand Dali, Dejan Lavbič and Dušan Omerčević. Applying Multi-Armed Bandit on top of content similarity recommendation engine
Igor Brigadir, Derek Greene and Padraig Cunningham. Adaptive Representations for Tracking Breaking News on Twitter
Jason Chuang, Sands Fish, David Larochelle, William Li and Rebecca Weiss. Large-Scale Topical Analysis of Multiple Online News Sources with Media Cloud
Nemanja Djuric, Mihajlo Grbovic and Dilan Gorur. How much do age and gender affect news topic preferences?
Raphael Gianotti Serrano Dos Santos and Estevam Hruschka Junior. Markov Logic Scalability in a Never-Ending Language Learning System
Nuno Moniz and Luís Torgo. Improvement of News Ranking through Importance Prediction
Aljaz Kosmerlj, Jenya Belyaeva, Gregor Leban, Blaz Fortuna and Marko Grobelnik. Crowdsourcing Event Extraction
James McInerney and David Blei. Discovering Newsworthy Tweets with a Geographical Topic Model
Catherine D'Ignazio, Rahul Bhargava, Ethan Zuckerman and Luisa Beck. CLIFF-CLAVIN: Determining Geographic Focus for News Articles
Long Le and Tina Eliassi-Rad. Measuring Coverage and Divergence of Reading Behaviors Among Friends
Jooyeon Kim, Joon Hee Kim, Dongwoo Kim and Alice Oh. Diversity-seeking users and their influence on social news sites
Jinjing Li and Wray Buntine. Experiments with Dynamic Topic Models
Also accepted for presentation:
Joseph G. Ellis, Brendan Jou, Hongzhi Li, Daniel Morozoff-Abegauz and Shih-Fu Chang. Structured Exploration of Who, What, When, and Where in Heterogeneous MultimediaNews Sources
We invite the submission of extended abstracts and we suggest keeping the paper
under 4 pages (NOT including references). For projects that require more room
for descriptions, we encourage
the authors to include details of the work as an appendix and/or other
supplementary materials. Please use the ACM style files and formatting
instructions. The submissions should include the authors' names and
affiliations since the review process will not be double blind. Topics that
were recently published or presented elsewhere are allowed, provided that the
extended abstract mentions this explicitly; topics that were presented in
non-machine learning and non-data mining conferences are especially encouraged.
Accepted submissions will be presented either as contributed talks or as posters.
In both cases use the Easychair submission site to upload your paper. We will
pursue a journal special issue with the topics of the workshop if we receive an
appropriate number of high-quality submissions.