Oct 6, 2014 – Oct 11, 2014
Silicon Valley, USA
Submission Deadline: Jul 21, 2014
Notification Due: Aug 21, 2014
Final Version Due: Aug 28, 2014
Description & Objectives
While content-based recommendation has been applied successfully in many different domains, it has not seen the same level of attention as collaborative filtering techniques have. In recent years, competitions like the Netflix Prize, CAMRA, and the Yahoo! Music KDD Cup 2011 have spurred on advances in collaborative filtering and how to utilize ratings and usage data. However, there are many domains where content and metadata play a key role, either in addition to or instead of ratings and implicit usage data. For some domains, such as movies the relationship between content and usage data has seen thorough investigation already, but for many other domains, such as books, news, scientific articles, and Web pages we do not know if and how these data sources should be combined to provide the best recommendation performance.
The aim of the CBRecSys 2014 workshop is to bring together students, faculty, researchers and professionals from both academia and industry who are interested in addressing one or more aspects of content-based recommendation. This would include both recommendation in domains where textual content is abundant (e.g., books, news, scientific articles, jobs, educational resources, Web pages, etc.) as well as dedicated comparisons of content-based techniques with collaborative filtering in different domains. Other relevant topics related to content-based recommendations could include opinion mining for text/book recommendation, semantic recommendation, content-based recommendation to alleviate cold-start problems, as well as serendipity, diversity and cross-domain recommendation.
To facilitate exploration of these topics the workshop will feature an in-workshop challenge on book recommendation. For this challenge a large dataset containing user profiles with book ratings and tags and 2.8 million book descriptions with library metadata, user ratings, tags, and reviews from Amazon and LibraryThing will be made available. The rich textual nature of the task makes the challenge an excellent venue to revisit the questions of the benefits of content-based filtering vs. collaborative filtering and metadata vs. ratings information.
Topics of interest
We invite original contributions in a variety of areas related to content-based recommendation. Topics of interest include, but are not limited to, the following:
* Processing text reviews
– Estimating (implicit) ratings associated with text reviews
– Opinion mining and sentiment analysis of text reviews to support content-based recommendation
– Extracting user personality traits and factors from text reviews for recommendation
* Exploiting user generated contents
– Social tag-based recommender systems
– Mining microblogging data in content-based recommender systems
– Exploiting Semantic Web and Linked Open Data in content-based recommender systems
* Mining contextual data from content
– Extraction of contextual signals from text contents for recommendation
– Considering the time dimension in content-based recommendation
– Mood- and sentiment-based recommender systems
* Addressing limitations of recommender system
– Addressing the cold-start problem with content-based recommendation approaches
– Increasing diversity in content-based recommendations
– Providing novelty in content-based recommendations
* Developing novel recommendation approaches
– Hybrid strategies combining content-based and collaborative filtering recommendations
– Content-based approaches to cross-system and cross-domain recommendation
– Latent factor models for content-based and hybrid recommendation
We encourage two types of submissions to the workshop: (1) submissions dedicated to one or more aspects of content-based recommendation, and (2) submissions describing their participation in the book recommendation challenge or that use the book recommendation data in an alternative manner. We encourage submissions from diverse backgrounds and aim to promote the exchange of ideas between researchers working in the abovementioned areas.
For both types of submissions, we welcome more mature ideas and approaches as long papers (8 pages) and preliminary work as short papers (4 pages).
For full details on the submission format and procedure, please refer to the Submissions page. Papers will be selected based on originality, quality, and ability to promote discussion. Accepted papers will be included in the workshop proceedings and published by CEUR. Extended versions of selected workshop papers may be included in a special journal issue (TBD). At least one author of each accepted paper must attend the workshop.
To facilitate exploration of these topics the workshop will feature an in-workshop challenge on book recommendation. For this challenge a large dataset containing user profiles with book ratings and tags and 2.8 million book descriptions with library metadata, user ratings, tags, and reviews from Amazon and LibraryThing will be made available. The rich textual nature of the task makes the challenge an excellent venue to revisit the questions of the benefits of content-based filtering vs. collaborative filtering and metadata vs. ratings information. Please consult the Challenge page for more details about the setup of the challenge and how to obtain the data set.
* First call for participation: May 5, 2014
* Challenge data set made available: May 12, 2014
* Paper submission deadline: July 21, 2014
* Challenge submission deadline: July 21, 2014
* Notification of acceptance: August 21, 2014
* Workshop & announcement of winners: RecSys 2014
Program Committee (TBC)
* Linas Baltrunas, Telefónica Research, Spain
* Alejandro Bellogín, Universidad Autónoma de Madrid, Spain
* Shlomo Berkovsky, NICTA, Australia
* Pablo Castells, Universidad Autónoma de Madrid, Spain
* Federica Cena, Universita’ degli Studi di Torino, Italy
* Tommaso Di Noia, Politecnico di Bari, Italy
* Peter Dolog, Aalborg University, Denmark
* Juan M. Fernández-Luna, Universidad de Granada, Spain
* Ignacio Fernández-Tobías, Universidad Autónoma de Madrid, Spain
* Cristina Gena, Universita’ degli Studi di Torino, Italy
* Juan F. Huete, Universidad de Granada, Spain
* Birger Larsen, Aalborg University, Denmark
* Pasquale Lops, University of Bari “Aldo Moro”, Italy
* Alan Said, Centrum Wiskunde & Informatica, The Netherlands
* Markus Schedl, Johannes Kepler University, Austria
* Giovanni Semeraro, University of Bari “Aldo Moro”, Italy
* Nava Tintarev, University of Aberdeen, UK
* Marko Tkalcic, University of Ljubljana, Slovenia
* David Vallet, Google, Australia
* Toine Bogers (firstname.lastname@example.org), Aalborg University Copenhagen, Denmark
* Marijn Koolen (email@example.com), University of Amsterdam, the Netherlands
* Iván Cantador (firstname.lastname@example.org), Universidad Autónoma de Madrid, Spain
For further questions please contact a member of the organizing committee.