=Paper=
{{Paper
|id=Vol-1618/INRA_preface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-1618/INRA_preface.pdf
|volume=Vol-1618
}}
==None==
https://ceur-ws.org/Vol-1618/INRA_preface.pdf
4th International Workshop on News Recommendation and
Analytics (INRA 2016)
http://research.idi.ntnu.no/inra/2016
Jon Atle Gulla Luc Martens Özlem Özgöbek
Department of Computer and iMinds-UGent-WiCa Department of Computer and
Information Science Ghent, Belgium Information Science
NTNU luc.Martens@intec.ugent.be NTNU
Trondheim, Norway Trondheim, Norway
jag@idi.ntnu.no ozlemo@idi.ntnu.no
Nafiseh Shabib Toon De Pessemier
TNS Gallup iMinds-UGent-WiCa
Oslo, Norway Ghent, Belgium
shabib@idi.ntnu.no toon.depessemier@ugent.be
ABSTRACT system domains like books, music and movies, news recom-
The 4th International Workshop on News Recommenda- mender systems have particular challenges which requires
tion and Analytics (INRA 2016) is held in conjunction with a deeper analysis of both the user, content and their rela-
UMAP 2016 Conference in Halifax, Canada. This workshop tionships. The news domain is characterized by a constant
aims to create an interdisciplinary community that addresses flow of unstructured, fragmentary, and unreliable news sto-
design issues in news recommender systems and news ana- ries from numerous sources and different perspectives. Some
lytics, and promote fruitful collaboration opportunities be- important challenges of news domain are:
tween researchers, media companies and practitioners. The
• Dynamic environment: Every hour hundreds of new
workshop includes a keynote speaker and an invited demo
articles is published by different sources,
presentation in addition to 4 papers accepted in this work-
shop. This paper presents a brief summary of the INRA
2016. • Faster changing user interests compared to other do-
mains. User interests in movies, music or books change
much slower than news,
Categories and Subject Descriptors
H.0 [Information Systems]: General • Willingness to read news articles that are independent
from user interests like breaking news,
Keywords
• Recency issues of news articles (people tend to read
Recommender systems; news recommendation; analytics recent news, not the old ones),
1. INTRODUCTION • Unstructured subjective content that create content
The motivation for news recommender systems is the tremen- analysis problems and may turn recommendations un-
dous amount of news articles available online and the dy- reliable.
namic nature of news domain. For a user it is getting harder
to reach the relevant news items according to her personal This workshop addresses primarily news recommender sys-
interests and preferences. News recommender systems aim tems and news analytics, with a particular focus on user pro-
to bring the most relevant news items to the users. filing and techniques for dealing with and extracting knowl-
Each domain in recommender systems has different char- edge from large-scale news streams. The news streams may
acteristics and requires different approaches to make suc- originate in large media companies, but may also come from
cessful recommendations. Compared to other recommender social sites, where user models are needed to decide how
user-generated content is to be taken into account. As part
of news recommendation and analytics, Big Data architec-
tures and large-scale statistical and linguistic techniques are
used to extract aggregated knowledge from large news streams
and prepare for personalized access to news. Personalization
and understanding the user behaviour/interests are also an
important part of news recommendation. In order to be
Copyright is held by the owner/author(s). able to give better recommendations we also keep focus on
INRA 2016 in conjunction with UMAP ’16, July 13-17, 2016, Halifax,
Canada constructing and maintaining the models of user preferences
. and interests within this workshop.
2. TOPICS OF INTEREST 3.2 Previous Workshops
Topics of interests for this workshop include but are not 4th International Workshop on News Recommendation
limited to: and Analytics (INRA 2016) is based on the following previ-
ous workshops:
• News semantics and ontologies,
• International News Recommender Systems Workshop
• News summarization, classification and sentiment anal- and Challenge (NRS)2 held in conjunction with the 7th
ysis, ACM Recommender Systems Conference in 2013. This
workshop had a very limited scope, which restricted
• Recommender systems and news personalization, the number of submissions and led to an acceptance
rate of 75%.
• Real-time news recommendation,
• International Workshop on News Recommendation and
• Robot journalism, Analytics (NRA) 2014 3 held in conjunction with 22nd
Conference on User Modelling, Adaptation and Per-
• User profiling and news context modeling, sonalization (UMAP) in 2014. The workshop scope
was extended with news analytics, which is closely
• News evolution and trends, lined with the field of news recommendation. The ac-
ceptance rate was 50%.
• Large-scale news mining and analytics,
• 3rd International Workshop on News Recommendation
and Analytics (INRA) 2015 4 4 held in conjunction
• Evaluation methods,
with ACM RecSys 2015 Conference in September 2015,
Vienna, Austria. Acceptance rate was 66%.
• News from social media,
• Big Data technologies for news streams, 4. ORGANIZERS
• News recommendation on mobile platforms. 4.1 Workshop Chairs
Jon Atle Gulla, Professor at Department of Computer
and Information Science, Norwegian University of Science
3. WORKSHOP DETAILS and Technology (NTNU), Norway
In INRA 2016 we have received 5 submissions, of which
4 were accepted for presentation. The submissions to our Luc Martens, Professor at iMinds-UGent-WiCa, Ghent,
workshop includes good quality of works for user interface Belgium
personalization, time issues in news recommender systems,
user engagement and a signal based approach to news rec-
ommendation. This year we have the acceptance rate of 4.2 Organizing Committee Co-Chairs
80%. In INRA 2016 we have a keynote speaker who has a Özlem Özgöbek, Department of Computer and Infor-
quite relevant academic background to news recommender mation Science, Norwegian University of Science and Tech-
systems and analytics. Our workshop also includes a demo nology (NTNU), Norway
session with Sugestio1 recommendation system which is de-
veloped in Ghent University. This system is a scalable and Xiaomeng Su, Department of Informatics and eLearn-
fault tolerant service to enrich content based websites with ing, Norwegian University of Science and Technology (NTNU),
the power of personalization. Norway
3.1 Keynote Speaker
Bei Yu is a Katchmar-Wilhelm Associate Professor of In- 4.3 Program Committee Co-Chairs
formation Studies at Syracuse University. Before joining SU Nafiseh Shabib, Digital Business Developer, TNS Gallup,
she was a postdoctoral fellow at Kellogg School of Manage- Oslo, Norway
ment, Northwestern University. She received her PhD in Li-
brary and Information Science in 2006 from the University Toon De Pessemier, iMinds-UGent-WiCa, Ghent, Bel-
of Illinois at Urbana-Champaign. She also holds Master’s gium
and Bachelor’s degrees in Computer Science. Her research
focuses on text mining, especially sentiment classification
and opinion mining, for social science research and digital
humanities. Bei Yu has given invited talks on the analy-
sis of language, gender, and opinion differences in political
speeches and documents. In 2009 she was the co-chair of the
First International Workshop on Topic-Sentiment Analysis
for Mass Opinion Measurement in Hong Kong, organized in
conjunction with the 18th ACM Conference on Information
2
and Knowledge Management. http://recsys.acm.org/recsys13/nrs
3
http://research.idi.ntnu.no/nra2014
1 4
http://www.sugestio.com/ http://research.idi.ntnu.no/inra/2015