<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<font size="-1">** apologies for cross-posting **<br>
<br>
==== Call for Challenge: 2nd Linked Open Data-enabled Recommender
Systems Challenge====<br>
<br>
Challenge Website:
<a class="moz-txt-link-freetext" href="http://sisinflab.poliba.it/events/lod-recsys-challenge-2015">http://sisinflab.poliba.it/events/lod-recsys-challenge-2015</a><br>
<br>
MOTIVATION AND OBJECTIVES<br>
People generally need more and more advanced tools that go beyond
those implementing the canonical search paradigm for seeking
relevant information. A new search paradigm is emerging, where the
user's perspective is completely reversed: from finding to being
found. <br>
Recommender systems may help to support this new perspective,
because they have the effect of pushing relevant objects, selected
from a large space of possible options, to potentially interested
users. To achieve this result, recommendation techniques generally
rely on data referring to three kinds of objects: users, items,
and their relations.<br>
Recent developments in the Semantic Web community offer novel
strategies to represent data about users, items and their
relations that might improve the current state of the art of
recommender systems, in order to move towards a new generation of
recommender systems which fully understand the items they deal
with.<br>
More and more semantic data are published following the Linked
Data principles, that enable links to be set up between objects in
different data sources, by connecting information in a single
global data space: the Web of Data. Today, the Web of Data
includes different types of knowledge represented in a homogeneous
form: sedimentary one (encyclopedic, cultural, linguistic,
common-sense) and real-time one (news, data streams, ...). These
data might be useful to interlink diverse information about users,
items, and their relations and implement reasoning mechanisms that
can support and improve the recommendation process.<br>
The primary goal of this challenge is twofold. On the one hand, we
want to enforce the link between the Semantic Web and the
Recommender Systems communities. On the other hand, we aim to
showcase how Linked Open Data and semantic technologies can boost
the creation of a new breed of knowledge-enabled and content-based
recommender systems.<br>
<br>
TARGET AUDIENCE<br>
The target audience is all of those communities, both academic and
industrial, which are interested in personalized information
access with a particular emphasis on Linked Open Data.<br>
During the last ACM RecSys conference the vast majority of
participants were from industry. This is evidence of the actual
interest of recommender systems for industrial applications ready
to be released in the market.<br>
<br>
DATA<br>
We collected data from Facebook profiles about three distinct
domains: movies, books and musical artists. After a process of
anonymization we then reconciled the data with DBpedia entities.
This data will be made available to train the recommendation
algorithms. In order to emphasize the usefulness of content-based
data, only "cold users" will be available in the dataset.<br>
<br>
TASKS<br>
- Task 1: Top-N recommendations from unary user feedback -<br>
This task deals with the top-N recommendation problem, in which a
system is requested to find and recommend a limited set of N items
that best match a user profile, instead of correctly predicting
the ratings for all available items. In order to favour the
proposal of content-based, LOD-enabled recommendation approaches,
and limit the use of collaborative filtering approaches, this task
aims to generate ranked lists of items for which only unary
feedback information (LIKE) is provided. For this task, we will
concentrate only on the movie domain.<br>
<br>
- Task 2: Diversity within recommended item sets -<br>
A very interesting aspect of content-based recommender systems,
and also of LOD-enabled ones, is providing the opportunity to
evaluate the diversity of recommended items in a straightforward
manner. This is a very popular topic in content-based recommender
systems, which usually suffer from over-specialization. In this
task, the evaluation will be made by considering a combination of
both accuracy of the recommendation list, and the diversity of
items belonging within it. Focusing on recommending musical
artists, we will consider diversity with respect to the
<a class="moz-txt-link-rfc2396E" href="http://dbpedia.org/ontology/genre"><http://dbpedia.org/ontology/genre></a>property.<br>
<br>
- Task 3: Cross-domain recommendation -<br>
This task aims to address a cross-domain recommendation scenario
in which user preferences and/or domain knowledge of a source
domain are used to recommend items in a different target domain.
This may correspond with the following use cases. The first refers
to the well known cold-start problem, which hinders the
recommendation generation due to the lack of sufficient
information about users or items. In a cross-domain setting, a
recommender may draw on information acquired from other domains to
alleviate such problem, e.g. a user’s favourite movie genres may
be derived from her favourite book genres. The second refers to
the generation of personalized cross-selling or bundle
recommendations for items from multiple domains, e.g. a movie
accompanied by a music album similar to the soundtrack of the
movie. These relations may not be extracted from rating
correlations within a joined movie-music rating matrix.<br>
In this task, we will request participants to exploit user
preferences and domain knowledge about movies, in order to provide
book recommendations.<br>
Making this task highly challenging, we will provide the list of
books available in the test set, but we will provide little
information about the users’ book preferences. Thus, we encourage
not (only) to use collaborative filtering strategies based on
correlations between movie and book preferences, but to
investigate approaches that exploit LOD relating both movies and
books domains.<br>
<br>
JUDGING AND PRIZES<br>
After a first round of reviews, the Program Committee and the
chairs will select a number of submissions that will have to
satisfy the challenge’s requirements, and will have to be
presented at the conference. Submissions accepted for presentation
will receive constructive reviews from the Program Committee, and
will be included in post-proceedings. All accepted submissions
will have a slot in a poster session dedicated to the challenge.
In addition, the winners will present their work in a special slot
of the main program of ESWC’15, and will be invited to submit a
chapter to a post-proceedings book published by Springer
(Communications in Computer and Information Science series).<br>
<br>
For each task we will select:<br>
* the best performing tool, given to the paper which will get the
highest score in the evaluation<br>
* the most original approach, selected by the Challenge Program
Committee with the reviewing process<br>
<br>
HOW TO PARTICIPATE<br>
We invite the potential participants to subscribe to our mailing
list in order to be kept up to date with the latest news related
to the challenge.<br>
<a class="moz-txt-link-abbreviated" href="mailto:lod-recsys-challenge-2015@googlegroups.com">lod-recsys-challenge-2015@googlegroups.com</a><br>
<br>
* Make your result submission<br>
- Register your group using the registration web form available at
<a class="moz-txt-link-freetext" href="http://dee020.poliba.it:8181/eswc2014lodrecsys/signup.html">http://dee020.poliba.it:8181/eswc2014lodrecsys/signup.html</a>.<br>
- Choose one or more tasks among Task1, Task2 and Task3 (see
Tasks).<br>
- Build your Recommendation System using the training data
described in section Dataset.<br>
- Evaluate your approach by submitting your results using the
evaluation service as described in section Evaluation.<br>
- Your final score will be the one computed with respect to the
last result submission made before March 25, 2015, 23:59 CET.<br>
<br>
* Submit your paper<br>
The following information has to be provided:<br>
- Abstract: no more than 200 words.<br>
- Description: It should contain the details of the system,
including why the system is innovative, how it uses Semantic Web,
which features or functions the system provides, what design
choices were made, and what lessons were learned. The description
should also summarize how participants have addressed the
evaluation tasks and the results evaluation. Papers must be
submitted in PDF format, following the style of the Springer’s
Lecture Notes in Computer Science (LNCS) series
(<a class="moz-txt-link-freetext" href="http://www.springer.com/computer/lncs/lncs+authors">http://www.springer.com/computer/lncs/lncs+authors</a>), and not
exceeding 12 pages in length.<br>
<br>
All submissions should be provided via EasyChair
<a class="moz-txt-link-freetext" href="https://www.easychair.org/conferences/?conf=eswc2015-challenges">https://www.easychair.org/conferences/?conf=eswc2015-challenges</a><br>
<br>
IMPORTANT DATES<br>
* Wednesday, March 25, 2015, 23:59 CET: Paper and Results
Submission due<br>
* Thursday, April 16, 2015, 23:59 CET: Notification of acceptance
and submission of task results<br>
* May 31- June 4, 2015: The Challenge takes place at ESWC-15<br>
<br>
<br>
CHALLENGE CHAIRS<br>
* Iván Cantador – Universidad Autónoma de Madrid, Spain<br>
* Tommaso Di Noia – Polytechnic University of Bari, Italy<br>
* Vito Claudio Ostuni – Pandora Media, Inc. USA<br>
* Matthew Rowe – University of Lancaster, UK<br>
<br>
PROGRAM COMMITTEE<br>
* Roi Blanco, Yahoo! Labs, Barcelona, Spain<br>
* Pablo Castells, Universidad Autónoma de Madrid, Spain<br>
* Miriam Fernández, The Knowledge Media Institute, The Open
University, UK<br>
* Ignacio Fernández-Tobías, Universidad Autónoma de Madrid, Spain<br>
* Frank Hopfgartner, Technische Universität Berlin, Germany<br>
* Julia Hoxha, Columbia University, USA<br>
* Dietmar Jannach, TU Dortmund University, Germany<br>
* Pasquale Lops, University of Bari Aldo Moro, Italy<br>
* Valentina Maccatrozzo, VU University Amsterdam, The Netherlands<br>
* Alexandre Passant, Clarity.fm, USA<br>
* Mariano Rico, Universidad Politécnica de Madrid, Spain<br>
* Giovanni Semeraro, University of Bari Aldo Moro, Italy<br>
* Manolis Wallace, University of Peloponnese, Greece<br>
* Markus Zanker, Alpen-Adria-Universitaet Klagenfurt, Austria <br>
<br>
TECHNICAL CHAIR<br>
* Paolo Tomeo, Polytechnic University of Bari, Italy<br>
<br>
ESWC CHALLENGE COORDINATORS<br>
* Elena Cabrio, INRIA Sophia-Antipolis Méditerranée, France<br>
* Milan Stankovic, Sépage & Université Paris-Sorbonne, France</font>
</body>
</html>