SeRSy 2012

International Workshop on Semantic Technologies meet Recommender Systems & Big Data

Scope

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 perspective is completely reversed: from finding to being found. 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.

Recent developments of 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.

More and more semantic data are published following the Linked Data principles, that enable to set up links between objects in different data sources, by connecting information in a single global data space: the Web of Data. Today, 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, ...). This 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.

The challenge is to investigate whether and how this large amount of wide-coverage and linked semantic knowledge can be automatically introduced into systems that perform tasks requiring human-level intelligence. Examples of such tasks include understanding a health problem in order to make a medical decision, or simply deciding which laptop to buy. Recommender systems support users exactly in those complex tasks.

The primary goal of the workshop is to showcase cutting edge research on the intersection of Semantic Technologies and Recommender Systems, by taking the best of the two worlds. This combination may provide the Semantic Web community with important real-world scenarios where its potential can be effectively exploited into systems performing complex tasks.

Topics

Topics of interest include (but are not limited to):

Accepted Papers

Invited Speaker

Ora Lassila

Bio: Ora Lassila is a Principal Technologist in Nokia's Big Data Analytics group where he worries about building systems for cataloguing and describing the multiple (big) data sets that make up Nokia's multi-petabyte data asset. Earlier, Dr. Lassila was a Research Fellow at Nokia Research Center where he pioneered the idea of the Semantic Web. He also dabbled in venture capitalism and has held research positions at MIT, CMU and Helsinki University of Technology. He holds a Ph.D in CS from the Helsinki University of Technology.

Size does not matter if your data is in a silo

Abstract: The advent of "big data" has afforded many opportunities for the discovery of interesting facts and phenomena about the world where this data was collected. Lots of excitement surrounds the systems and platforms which are used in processing big data (and indeed, which are capable of the scale needed). Some of the technical optimizations needed for scaling up processing (e.g., NoSQL, key/value databases) have resulted in "weaker" or less accessible data models, and consequently tend to emphasize the notion of "siloed" data. To mitigate this, we need stronger effort on how data is described, both in terms of operational parameters, provenance, workflows, and rich data models. Semantic Web technologies are well suited to capturing all the metainformation needed, regardless of the physical formats and storage solutions used for the actual data.

Program

9:00 - 9:10
Introduction.
9:10 - 9:50
Ora Lassila
Size does not matter if your data is in a silo
9:50 - 10:10
Xueyan Jiang, Volker Tresp, Yi Huang and Maximilian Nickel
Link Prediction in Multi-relational Graphs using Additive Models.
10:10 - 10:30
Rahul Parundekar and Kentaro Oguchi
Driver Recommendations of POIs using a Semantic Content-based Approach.
10:30 - 11:00
Coffee Break
11:00 - 11:20
Marco Fossati, Claudio Giuliano and Giovanni Tummarello
Semantic Network-driven News Recommender Systems: a Celebrity Gossip Use Case.
11:20 - 11:40
Vito Claudio Ostuni, Tommaso Di Noia, Roberto Mirizzi, Romito Davide and Eugenio Di Sciascio
Cinemappy: a Context-aware Mobile App for Movie Recommendations boosted by DBpedia.
11:40 - 12:00
Jeremy Debattista, Simon Scerri, Ismael Rivera and Siegfried Handschuh
Ontology-based Rules for Recommender Systems.
12:00 - 12:20
Marco Rospocher and Luciano Serafini
Ontology-centric decision support.
12:20 - 12:40
Miguel Lagares Lemos, Daniel Villanueva Vasquez, Mateusz Radzimski, Angel Lagares Lemos and Juan Miguel Gómez-Berbís
RING: A Context Ontology for Communication Channel Rule-based Recommender System.

Proceedings

The workshop proceedings have been published as CEUR-WS Vol-919 and are avilable at http://ceur-ws.org/Vol-919

Submission

We welcome work at all stages of development: papers can describe applied systems, empirical results or theoretically grounded positions.

Accepted papers will be published as CEUR workshop proceedings (http://ceur-ws.org).

Based on the quality of accepted papers we are planning to schedule a special issue of a top-level journal in 2013.

* Full papers (10-12 pages)

* Short papers (4-6 pages)

* Demos (2-4 pages for description)

Papers should be formatted according to the general ISWC2012 submission guidelines. Accepted format is PDF.

Please submit your paper via EasyChair at the following URL:

https://www.easychair.org/conferences/?conf=sersy2012

You need to open a personal account upon the first login, if you do not have one.

Important Dates

Organizing Commitee

Program Committee

Contacts

Hosted by Sisinf Lab. Design by Andreas Viklund.