Recommender Systems - RecSysrecsys.acm.org/wp-content/uploads/2015/08/RecSys... · the submitted...

The ACM Conference Series onRecommender Systems

9th ACM Conference on Recommender Systems

Conference Program

Sept 16-20, 2015

RECSYSVIENNA2015

32

WelcomeOur very warm welcome to the 9th ACM Recommender Systems Con-ference (ACM RecSys 2015), held between September 16th and 20th, in Vienna, Austria. The RecSys conference series has clearly established it-self as the premier international forum for research and development in the field of Recommender Systems, where leading researchers and practitioners from academia and industry meet to share their challenges, solutions, research results, and experiences in the field.

The maturity of the conference is demonstrated by the high quality of the submitted research work. This year RecSys received again more than 200 submissions (131 long papers and 84 short papers) and the review process was fairly selective. The Program Committee worked very hard to ensure that every paper got at least three careful and fair reviews as well as one metareview. All papers, particularly those at the borderline, were also reviewed and thoroughly discussed by a Senior Program Committee member and by the PC Chairs. This process finally led to the accept-ance of 28 long papers for oral presentation (acceptance rate 21,4%) and 22 short papers for poster presentation (acceptance rate 26,2%). We are therefore especially grateful to our 131 Program Committee members (34 senior and 97 regular) and to our 57 additional reviewers for pro-ducing more than 875 detailed and insightful reviews and meta-reviews. Furthermore, we would like to particularly thank those Senior Program Committee members, who assisted the program chairs in identifying those distinguished papers that received awards.

Besides the technical paper program consisting of oral presentations and a poster and demo session, the core conference program also includes two keynote speeches, two industry sessions and a panel discussion. In order to accommodate the program in a two and a half day format, tech-nical papers are presented in two parallel tracks for the first time in this conference series. In addition, the conference includes four tutorials and a challenge as a pre-conference program and nine workshops as well as a doctoral symposium as post-conference events.

We also would like to take this opportunity to thank all our colleagues, who volunteered their time to contribute to the success of this confer-ence, as well as acknowledge the support from our sponsors and network partners, who generously provided funds and services which are crucial for the organization of this event. This conference would also not be possible without the dedication, devotion and hard work of the members of our organizing committee. Our special thanks extend to all of them. Finally, we want to acknowledge the EasyChair infrastructure for the man-agement of the review process.

Please join us at RecSys 2015 to interact with experts from academia and industry on topics related to recommender systems and to experience and share new research findings, best practices, state-of-the-art systems and applications of recommender systems.

Hannes Werthner General Co-Chair

Markus ZankerGeneral Co-Chair

Jennifer GolbeckProgram Co-Chair

Giovanni SemeraroProgram Co-Chair

Werner Geyer Industry Co-Chair

Domonkos TikkIndustry Co-Chair

54

Venue - TU WienThe conference will be held at the Technische Universität Wien (TU Wien), located close to the historic center of Vienna and a few meters away from the Vienna opera house, the St. Charles’ Church and the subway station Karlsplatz.

The main part of the conference will take place in the Freihaus building.

How to get there

The TU Wien can be reached by » subway number U1 (red line), U2 (purple line), U4 (green line):

station Karlsplatz » tram number 1, 62: station Resselgasse » tram number 1, 2, D, 62: station Kärntner Ring/Oper

Vienna’s public transport authority is Wiener Linien. A one-way ride costs 2.20 EUR, a 24-hour ticket costs 7.60 EUR, and a weekly ticket costs 16.20 EUR. You can use the same ticket for all subway lines as well as for all trams and busses. For more information see the website of Vienna‘s public transport authority: www.wienerlinien.at.

TU Wien Main Building

TU Wien Freihaus Building

6 7

The Conference HallsFirst Floor

GREEN AREA YELLOW AREA RED AREA

SEM 101A

Second Floor

Third Floor

@ Freihaus

STAIRS STAIRS

STAIRS

POSTER AREA

POSTER AREA


HS 1

HS 2HS 3HS 4

HS 7

HS 5

HS 6

STAIRS

STAIRS

STAIRS


REGISTRATION

MENSA

EXHIBITION AREA

EXHIBITION AREA

HS 1

8 9

Wednesday 16th Thursday 17th Friday 18th

08:00-09:00Registration Registration Registration

09:00-09:30Tutorial

Replicable Evaluation of Recommender Systems

HS 5

Tutorial Real-time Recommendation of

Streamed Data

HS 6

Challenge

HS 3

Session 2a

Contextual Challenges

HS 1

Session 2b

Cold Start and Hybrid RS

HS 5

Session 4a

Novel Setups

HS 1

Session 4b

Algorithms

HS 5

09:30-10:00

10:00-10:30

10:30-11:00Break Break Break

11:00-11:30Tutorial

Scalable Recommender Systems: Where Machine Learning Meets Search!

HS 5

TutorialInteractive Recommender

Systems

HS 6

Challenge

HS 3

Session 3

Distinguished Papers

HS 1

Keynote“Recommendations within a Social Network:

One Step at a Time” by Igor Perisic

HS 1

11:30-12:00

12:00-12:30

12:30-13:00Lunch Break Lunch Break Lunch Break

13:00-13:30

13:30-14:00Opening Remarks

&

Keynote “A (Persuasive?) Speech on Automated Persuasion”

by Oliviero Stock

HS 1

14:00-14:30Industry Session 1

HS 1

Industry Session 2

HS 114:30-15:00

15:00-15:30

15:30-16:00Break

16:00-16:30Session 1a

The User in the Loop

HS 1

Session 1b

RS and Social Networks

HS 5

Break Break

16:30-17:00Industry Panel Discussion

HS 1

Session 5a

News and Media

HS 1

Session 5b

E-commerce & Ads

HS 5

17:00-17:30

17:30-18:00Short Paper and Demo Slam

HS 118:00-18:30Transfer Closing & Farewell

18:30-19:00Transfer

19:00-19:30Conference ReceptionPoster/Demo Session

TU Main Building / Prechtlsaal

Conference DinnerDinner Speech by

Swaminathan VishwanathanVienna City Hall

19:30-20:00

Steering Committee DinnerGlacis Beisl Museumsquartier

20:00-22:00

Schedule

HS 1, 3, 4, 5, 6, 7 | SEM 101A are situated in the Freihaus building

Wed - Fri

supported by

supported by

supported by

supported by supported by

supported by

supported by


supported by

supported by

supported by

supported bysupported by

10 11

Saturday 19th Sunday 20th

08:00-09:00Registration Registration

09:00-09:30Doctoral

Symposium

SEM 101A

W: LocalRec

HS 5

W: IntRS

HS 3

W: RecSysTV

HS 7

W: EMPIRE

HS 4

W: CBRecSys

HS 6

W: LSRS

HS 5

W: TouRS15

HS 7

W: INRA

HS 4

09:30-10:00

10:00-10:30

10:30-11:00Break Break

11:00-11:30Doctoral

Symposium

SEM 101A

W: LocalRec (cont.)

HS 5

W: IntRS(cont.)

HS 3

W: RecSysTV(cont.)

HS 7

W: EMPIRE(cont.)

HS 4

W: CBRecSys(cont.)

HS 6

W: LSRS(cont.)

HS 5

W: TouRS15(cont.)

HS 7

W: INRA(cont.)

HS 4

11:30-12:00

12:00-12:30

12:30-13:00Lunch Break Lunch Break

13:00-13:30

13:30-14:00

14:00-14:30Doctoral

Symposium

SEM 101A

W: CrowdRec

HS 5

W: IntRS(cont.)

HS 3

W: RecSysTV(cont.)

HS 7

W: CBRecSys(cont.)

HS 6

W: LSRS(cont.)

HS 5

W: TouRS15(cont.)

HS 7

14:30-15:00

15:00-15:30

15:30-16:00Break Break

16:00-16:30Doctoral

Symposium

SEM 101A

W: CrowdRec (cont.)

HS 5

W: IntRS(cont.)

HS 3

W: RecSysTV(cont.)

HS 7

W: CBRecSys(cont.)

HS 6

W: LSRS(cont.)

HS 5

W: TouRS15(cont.)

HS 7

16:30-17:00

17:00-17:30

Schedule

Tutorial

Challenge

Keynote / Technical Session

Industry Session

Doctoral Symposium

Workshop (W)

Social Event

HS 1, 3, 4, 5, 6, 7 | SEM 101A are situated in the Freihaus building

Sat - Sun

12 13

Keynotes

Oliviero StockFBK-IRST, Italy

A (Persuasive?) Speech on Automated Persuasion

Philosophers of language have taught us that at the basis of language production there is the intention to change the state of the world by intervening linguistically on other agents. Persuasion, being the process of influencing attitudes, beliefs, behaviors, mood of a target, is a matter of stronger emphasis. Argumentation is just one resource to persuasion, it has been studied since the times of Aristotle and now for quite some time in artificial intelligence. In modern times we have witnessed also resorting to what is called a peripheral route to persuasion. Automated intelligent persuasion of this sort (and also defense from inappropriate persuasion) is a research area close to producing usable results, both through creative production of language expressions, and through other forms of communication. The theme is sensitive and so it is equally im-portant to address ethical acceptability of persuading machines. The talk makes reference to concrete studies conducted within the Per Te project.

ABOUT THE SPEAKER

Oliviero Stock has been at IRST since 1988 and has been its director from 1997 to 2001. His activity is mainly in artificial intelligence, natural language processing, intelligent user interfaces, cognitive technologies, computational creativity. He is the author of over two hundred and fifty peer-reviewed papers and author or editor of twelve volumes, and has been a member of the editorial board of a dozen scientific journals. He has been Chairman of the European Coordinating Committee for Artifi-cial Intelligence (ECCAI), President of the Association for Computational Linguistics and of the Italian AI Association and is an ECCAI and a AAAI Fellow. Since 2012 he has been directing the Per Te project concerned with various aspects of intelligent persuasion technologies.

Igor PerisicLinkedIn, USA

Recommendations within a Social Network: One Step at a Time

Machine Learning and Recommender systems at LinkedIn are leveraged to optimize our members’ experience across all of LinkedIn’s value prop-ositions. Whether it is about helping job seekers find a new opportunity or keeping our members connected with the people or knowledge that matter most to them professionally, recommender systems and relevance science provide us with the ability to make that experience personal and relevant. Relevance within the context of this value proposition or busi-ness object is a requirement that at times is non-trivial to translate into an optimization function.

In this talk, Dr. Perisic will present work that his teams have done over the past few years in developing models and their supporting infrastruc-ture to attempt to resolve a variety of problems across many of Linke-dIn’s value propositions. The presentation will use a couple of use cases from LinkedIn to showcase issues, „The Good, The Bad and The Ugly“, his teams has faced while attempting to optimize a member’s experience. These will cover both real-time and offline cases as well as what arises when you mix them.

ABOUT THE SPEAKER

Igor Perisic joined LinkedIn in 2007 after a brief stay at Microsoft and is currently a Vice President of Engineering. Through his tenure at Linke-dIn, his teams developed LinkedIn’s Search Engine, its Real-Time Graph Engine, Relevance infrastructure and worked on personalizing LinkedIn’s site for its members. To provide LinkedIn’s members with data products, such as like People You May Know or Jobs You May Be Interested In, his team has built through open source technologies and contributed back to it with projects such as Kafka, Voldemort or extensions such as ml-ease and many others.

Wednesday Sept 16, 14:00 - 15:30, HS 1Moderator: Hannes Werthner

Friday Sept 18, 11:00 - 12:30, HS 1Moderator: Markus Zanker

Keynotes


14 15

Replicable Evaluation of Recommender Systems

Recommender systems research is by and large based on comparisons of recommendation algorithm’s predictive accuracy: the better the eval-uation metrics (higher accuracy scores or lower predictive errors), the better the recommender algorithm. Comparing the evaluation results of two recommendation approaches is however a difficult process as there are very many factors to be considered in the implementation of an al-gorithm, its evaluation, and how datasets are processed and prepared.

This tutorial will show how to present evaluation results in a clear and concise manner, while ensuring that the evaluation results are compa-rable, replicable and unbiased. These insights are not limited to recom-mender systems research alone, but are also valid for experiments with other types of personalized interactions and contextual information.

Wednesday Sept 16, 09:00 - 10:30, HS 5

Real-time Recommendation of Streamed Data

This tutorial addresses two trending topics in the field of recommender systems research: online evaluation in the form of A/B testing and offline evaluation of streamed-based recommendation techniques.

A/B testing aims to benchmark varieties of a recommender system by a larger group of users. It is increasingly adopted for the evaluation of commercial systems with a large user base as it provides the advantage of observing the efficiency of recommendation algorithms under real conditions. However, while online evaluation is the de-facto standard evaluation methodology in Industry, university-based researchers often do not have access to either infrastructure or user base to perform on-line evaluation on a larger scale. Addressing this deficit, participants will learn how they can join a living lab on news recommendation that allows them to perform A/B testing.

Offline evaluation allows for the evaluation of research hypotheses that center around modeling recommendation as user-specific selection from static collections of items. While this might be suitable in some domains where the content does not change too often, it fails in more dynamic domains where items continuously emerge and extend collections, and where existing items become less and less relevant. Examples include news, microblog, or advertisement recommendations where content comes in the form of a constant stream of data. Streamed data triggers specific challenges for recommender systems. For example, it challenges collaborative filtering as this imposes that the sets of users and items rapidly fluctuate. This tutorial focuses on stream-based recommenders that reflect these dynamics.

TutorialsWednesday Sept 16, 09:00 - 10:30, HS 6

Alan SaidRecorded Future, Sweden

Alejandro BellogínUniversidad Autónoma de Madrid, Spain

Frank HopfgartnerUniversity of Glasgow, UK

Benjamin KilleTU Berlin, Germany

Tobias Heintzplista GmbH, Germany

Roberto TurrinContentWise, Italy

Tutorials

Francesco RicciTutorial Co-Chair

Alexander TuzhilinTutorial Co-Chair

16 17

Scalable Recommender Systems: Where Machine Learning Meets Search!

This tutorial gives an overview of how search engines and machine learn-ing techniques can be tightly coupled to address the need for building scalable recommender or other prediction based systems. Typically, most of them architect retrieval and prediction in two phases. In Phase I, a search engine returns the top-k results based on constraints expressed as a query. In Phase II, the top-k results are re-ranked in another sys-tem according to an optimization function that uses a supervised trained model. However this approach presents several issues, such as the pos-sibility of returning sub-optimal results due to the top-k limits during query, as well as the prescence of some inefficiencies in the system due to the decoupling of retrieval and ranking.

To address this issue the authors created ML-Scoring, an open source framework that tightly integrates machine learning models into Elastic-search, a popular search engine. ML-Scoring replaces the default infor-mation retrieval ranking function with a custom supervised model that is trained through Spark, Weka, or R that is loaded as a plugin in Elas-ticsearch. This tutorial will not only review basic methods in information retrieval and machine learning, but it will also walk through practical examples from loading a dataset into Elasticsearch to training a model in Spark, Weka, or R, to creating the ML-Scoring plugin for Elasticsearch. No prior experience is required in any system listed (Elasticsearch, Spark, Weka, R), though some programming experience is recommended.


Interactive Recommender Systems

Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation ex-perience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direc-tion.

In particular, we will explore the field of interactive video and music rec-ommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.

The tutorial targets researchers and practitioners in the field of recom-mender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.

TutorialsWednesday Sept 16, 11:00 - 12:30, HS 6

Joaquin A. DelgadoVerizon, US

Diana Hu Verizon, US

Harald Steck Netflix Inc., US

Roelof van Zwol Netflix Inc., US

Chris JohnsonSpotify Inc., US

Tutorials

18 19

In this year’s edition of the RecSys Challenge, YOOCHOOSE is providing a collection of sequences of click events; click sessions. For some of the sessions, there are also buying events. The goal is hence to predict whether the user (a session) is going to buy something or not, and if he is buying, what would be the items he is going to buy. Such an infor-mation is of high value to an e-business as it can indicate not only what items to suggest to the user but also how it can encourage the user to become a buyer. For instance to provide the user some dedicated pro-motions, discounts, etc. The data represents six months of activities of a big e-commerce businesses in Europe selling all kinds of stuff such as garden tools, toys, clothes, electronics and much more.


Challenge

David Ben-Shimon YooChoose Labs, Israel

Michael FriedmanYooChoose GmbH, Germany

Alexander TsikinovskyYooChoose Labs, Israel

Johannes HörleYooChoose GmbH, Germany

Lior Rokach Ben Gurion University of the Negev, Israel

Bracha ShapiraBen Gurion University of the Negev, Israel

Session 1a: The User in the Loop

Wed Sept 16, 16:00 - 17:30 HS 1 Chair: Marco de Gemmis

Putting Users in Control of their Recommendations F. Maxwell Harper, Funing Xu, Harmanpreet Kaur, Kyle Condiff, Shuo Chang and Loren Terveen

Letting Users Choose Recommender Algorithms: An Experimental Study

Michael D. Ekstrand, Daniel Kluver, F. Maxwell Harper and Joseph A. Konstan

“I like to explore sometimes” — Adapting to Dy-namic User Novelty Preferences

Komal Kapoor, Vikas Kumar, Loren Terveen, Joseph A. Konstan and Paul Schrater

Technical Sessions

Session 1b: Recommender Systems and Social Networks

Wed Sept 16, 16:00 - 18:00 HS 5 Chair: Bamshad Mobasher

Overlapping Community Regularization for Rating Prediction in Social Recommender Systems

Hui Li, Dingming Wu, Wenbin Tang and Nikos Mamoulis

Preference-oriented Social Networks: Group Rec-ommendation and Inference

Amirali Salehi-Abari and Craig Boutilier

A Probabilistic Model for Using Social Networks in Personalized Item Recommendation

Allison J.B. Chaney, David M. Blei and Tina Eliassi-Rad

PushTrust: An Efficient Recommendation Algorithm by Leveraging Trust and Distrust Relations

Rana Forsati, Iman Barjasteh, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

20 21

Technical SessionsSession 2a: Contextual Challenges

Thu Sept 17, 09:00 - 10:30 HS 1 Chair: Francesco Ricci

Top-N Recommendation for Shared Accounts Koen Verstrepen and Bart Goethals

Exploiting Geo-Spatial Preference for Personal-ized Expert Recommendation

Haokai Lu and James Caverlee

Risk-Hedged Venture Capital Investment Recom-mendation

Xiaoxue Zhao, Weinan Zhang and Jun Wang

Session 2b: Cold Start and Hybrid Recommender Systems

Thu Sept 17, 09:00 - 10:30 HS 5 Chair: George Karypis

ExcUseMe: Asking Users to Help in Item Cold-Start Recommendations

Michal Aharon, Oren Anava, Noa Avigdor-Elgrabli, Dana Drachsler-Cohen, Shahar Golan, and Oren Somekh

Cold-Start Item and User Recommendation with Decoupled Completion and Transduction

Iman Barjasteh, Rana Forsati, Farzan Masrour, Abdol-Hossein Esfahanian and Hayder Radha

HyPER: A Flexible and Extensible Probabilistic Framework for Hybrid Recommender Systems

Pigi Kouki, Shobeir Fakhraei, James Foulds, Magdalini Eirinaki and Lise Getoor

Session 3: Distinguished Papers

Thu Sept 17, 11:00 - 12:30 HS 1 Chair: Giovanni Semeraro

Applying Differential Privacy to Matrix Factori-zation

Arnaud Berlioz, Arik Friedman, Mohamed Ali Kafaar, Roksana Boreli and Shlomo Berkovsky

Gaussian Ranking by Matrix Factorization Harald Steck

Context-Aware Event Recommendation in Event-based Social Networks

Augusto Q. Macedo, Leandro B. Marinho and Rodrygo L. T. Santos

Technical SessionsSession 4a: Novel Setups

Fri Sept 18, 09:00 - 10:30 HS 1 Chair: Dietmar Jannach

It Takes Two to Tango: an Exploration of Domain Pairs for Cross-Domain Collaborative Filtering

Shaghayegh Sahebi and Peter Brusilovsky

Recommending Fair Payments for Large-Scale Social Ridesharing

Filippo Bistaffa, Alessandro Farinelli, Georgios Chalkiadakis and Sarvapali D. Ramchurn

Learning Distributed Representations from Re-views for Collaborative Filtering

Amjad Almahairi, Kyle Kastner, Kyunghyun Cho and Aaron Courville

Session 4b: Algorithms

Fri Sept 18, 09:00 - 10:30 HS 5 Chair: Gedas Adomavicius

Dynamic Poisson Factorization Laurent Charlin, Rajesh Ranganath, James McInerney and David M. Blei

Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks

Fabian Christoffel, Bibek Paudel, Chris Newell and Abraham Bernstein

Fast Differentially Private Matrix Factorization Ziqi Liu, Yu-Xiang Wang and Alexander J. Smola

22 23

Technical SessionsSession 5a: News and Media

Fri Sept 18, 16:30 - 18:00 HS 1 Chair: Tsvi Kuflik

Predicting Online Performance of News Rec-ommender Systems Through Richer Evaluation Metrics

Andrii Maksai, Florent Garcin and Boi Faltings

Beyond “Hitting the Hits” – Generating Coher-ent Music Playlist Continuations with the Right Tracks

Dietmar Jannach, Lukas Lerche and Iman Kamehkhosh

Content Driven User Profiling for Comment-Wor-thy Recommendations of News and Blog Articles

Trapit Bansal, Mrinal Das and Chiranjib Bhattacharyya

Session 5b: E-commerce & Ads

Fri Sept 18, 16:30 - 18:00 HS 5 Chair: Paolo Cremonesi

Selection and Ordering of Linear Online Video Ads

Wreetabrata Kar, Viswanathan Swaminathan and Paulo Albuquerque

Adaptation and Evaluation of Recommendations for Short-term Shopping Goals

Dietmar Jannach, Lukas Lerche and Michael Jugovac

E-commerce Recommendation with Personalized Promotion

Qi Zhao, Yi Zhang, Daniel Friedman and Fangfang Tan

Session 1: Media and TV, People and Skills

Thu Sept 17, 14:00 - 16:00 HS 1 Chair: Domonkos Tikk

Personalized Catch-up & DVR: VOD or Linear, That is the Question

Pancrazio Auteri (Moviri/ContentWise)

Recommendations for Live TV Jan Neumann & Hassan Sayyadi (Comcast)

The Application of Recommender Systems in a Multi Site, Multi Domain Environment

Steven Bourke (Schibsted)

We Know Where You Should Work Next Summer: Job Recommendations

Fabian Abel (XING)

Assessing Expertise in the Enterprise: The Re-commender Point of View

Aleksandra (Saška) Mojsilovic (IBM Research)

Industry Sessions

Session 2: Generic Platforms and Location-based Application Domains

Fri Sept 18, 14:00 - 16:00 HS 1 Chair: Werner Geyer

Large-Scale Real-Time Product Recommendation At Criteo

Romain Lerallut (Criteo)

Scaling up Recommendation Services in Many Dimensions

Bottyán Németh (Gravity R&D)

Recommendations in Travel Onno Zoeter (Booking.com)

Making Meaningful Restaurant Recommenda-tions At OpenTable

Sudeep Das (OpenTable)

The Role of User Location in Personalized Search and Recommendation

Ido Guy (Yahoo Labs)

supported by

24 25

Industry SessionsPanel Discussion: Start-ups in the Arena of Recommender Systems

Thu Sept 17, 16:30 - 18:00 HS 1

Moderators: Domonkos Tikk (CEO at Gravity R&D, Hungary), Hannes Werthner (Profes-sor of E-commerce at TU Wien, Austria)

Oliver Holle, CEO at SpeedInvest, Austria

Barry Smith, Digital Professor of Computer Science at UCD School of Computer Science and Informatics, Ireland

Robert Wetzker, CEO at Aklamio, Germany

Tao Ye, Senior Scientist at Pandora, USA

Jeremy York, Principal Data Scientist at RichRelevance, USA

Short PapersShort Paper and Demo Slam

Wed Sept 16, 17:30 - 18:30 HS 1 Chair: Alejandro Bellogín

2 minutes elevator pitches of short papers and demos

Poster/Demo Session

Wed Sept 16, 19:00 - 22:00 TU Main Building, Prechtlsaal

Posters and demos are exhibited during the reception

Poster Area

Thu Sept 17 - Fri Sept 18 TU Freihaus, 2nd floor

Posters are exhibited in the desig-nated poster area

A Study of Priors for Relevance-Based Language Modelling of Recommender SystemsDaniel Valcarce, Javier Parapar and Álvaro Barreiro

Adapting Recommendations to Contextual Changes Using Hierarchical Hidden Markov ModelsMehdi Hosseinzadeh Aghdam, Negar Hariri, Bamshad Mobasher and Robin Burke

Are Real-World Place Recommender Algorithms Useful in Virtual World Environments?Leandro Balby Marinho, Christoph Trattner and Denis Parra

Asymmetric Recommendations: The Interacting Effects of Social Ratings’ Direction and Strength on Users’ RatingsOded Nov and Ofer Arazy

Crowd Sourcing, with a Few Answers: Recommending Commuters for Traffic UpdatesElizabeth M. Daly, Michele Berlingerio and François Schnitzler

Data Quality Matters in Recommender SystemsOren Sar Shalom, Shlomo Berkovsky, Royi Ronen, Elad Ziklik and Amir Amihood

Elsevier Journal Finder: Recommending Journals for your PaperNing Kang, Marius Doornenbal and Bob Schijvenaars

Evaluating Tag Recommender Algorithms in Real-World Folksonomies: A Comparative StudyDominik Kowald and Elisabeth Lex

supported by

26 27

Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social TaggingSantiago Larrain, Christoph Trattner, Denis Parra, Eduardo Graells-Garrido and Kjetil Nørvåg

Improving the User Experience during Cold Start through Choice-Based Preference Elicita-tionMark P. Graus and Martijn C. Willemsen

Incremental Matrix Factorization via Feature Space Re-learning for Recommender SystemQiang Song, Jian Cheng and Hanqing Lu

Latent Trajectory Modeling: A Light and Efficient Way to Introduce Time in Recommender SystemsElie Guàrdia-Sebaoun, Vincent Guigue and Patrick Gallinari

Making the Most of Preference Feedback by Modeling Feature DependenciesS Chandra Mouli and Sutanu Chakraborty

Nudging Grocery Shoppers to Make Healthier ChoicesElizabeth Wayman and Sriganesh Madhvanath

Nuke ’Em Till They Go: Investigating Power User Attacks to Disparage Items in Collabora-tive RecommendersCarlos E. Seminario and David C. Wilson

“Please, Not Now!” A Model for Timing RecommendationsNofar Dali Betzalel, Bracha Shapira and Lior Rokach

POI Recommendation: Towards Fused Matrix Factorization with Geographical and Tempo-ral InfluencesJean-Benoît Griesner, Talel Abdessalem and Hubert Naacke

The Recommendation Game: Using a Game-with-a-Purpose to Generate Recommendation DataSam Banks, Rachael Rafter and Barry Smyth

Top-N Recommendation with Missing Implicit FeedbackDaryl Lim, Julian McAuley and Gert Lanckriet

Towards Automatic Meal Plan Recommendations for Balanced NutritionDavid Elsweiler and Morgan Harvey

Uncovering Systematic Bias in Ratings across Categories: a Bayesian ApproachFangjian Guo and David B. Dunson

User Churn Migration Analysis with DEDICOMRafet Sifa, César Ojeda and Christian Bauckhage

Short Papers Demos

A Personalised Reader for Crowd Curated ContentGabriella Kazai, Daoud Clarke, Iskander Yusof, Matteo Venanzi

Automated Recommendation of Healthy, Personalised Meal PlansMorgan Harvey, David Elsweiler

CNARe: Co-authorship Networks Analysis and Recommendations Guilherme A. de Sousa, Matheus A. Diniz, Michele A. Brandão and Mirella M. Moro

Event Recommendation using Twitter ActivityAxel Magnuson, Vijay Dialani, Deepa Mallela

Health-aware Food Recommender System Mouzhi Ge, Francesco Ricci, David Massimo

Kibitz: End-to-End Recommendation System BuilderQuanquan Liu, David R. Karger

OSMRec Tool for Automatic Recommendation of Categories on Spatial Entities in Open-StreetMap Nikos Karagiannakis, Giorgos Giannopoulos, Dimitrios Skoutas, Spiros Athanasiou

Short Paper and Demo Slam

Wed Sept 16, 17:30 - 18:30 HS 1 Chair: Alejandro Bellogín

2 minutes elevator pitches of short papers and demos

Poster/Demo Session



Poster Area


Posters of the demos are exhibited in the designated poster area

Pablo CastellsPoster and Demo Chair

28 29

Posters

A Recommendation-Based Book-Exchange System Without Using Wish ListsMaria Soledad Pera and Yiu-Kai Ng

Analysing Compression Techniques for In-Memory Collaborative FilteringSaúl Vargas, Craig Macdonald and Iadh Ounis

Analysis of User-generated Content for Improving YouTube Video RecommendationMichele Galli, Davide Feltoni Gurini, Fabio Gasparetti, Alessandro Micarelli and Giuseppe Sansonetti

Comparing offline and online recommender system evaluations on long-tail distributionsGabriel de Souza Pereira Moreira, Gilmar Alves de Souzaand Adilson Cunha

Do you have a Pop face? Here is a Pop song. Using profile pictures to mitigate the cold-start problem in Music Recommender Systems.Eugenio Tacchini, Ramon Morros, Veronica Vilaplana and Enrique Sañoso

Exploiting Latent Social Listening Representations for Music RecommendationsChih-Ming Chen, Po-Chuan Chien, Ming-Feng Tsai, Yi-Hsuan Yang and Yu-Ching Lin

Exploiting Reviews to Guide Users’ Selections Nevena Dragovic and Maria Soledad Pera

How to Interpret Implicit User Feedback?Ladislav Peska and Peter Vojtas

Image Discovery and Insertion for Custom PublishingLei Liu, Jerry Liu and Shanchan Wu

Item Familiarity Effects in User-Centric Evaluations of Recommender SystemsDietmar Jannach, Lukas Lerche and Michael Jugovac

Measuring the Concentration Reinforcement Bias of Recommender SystemsPanagiotis Adamopoulos, Alexander Tuzhilin and Peter Mountanos

Merging Latent Factors and Tags to Increase Interactive Control of RecommendationsTim Donkers, Benedikt Loepp and Jürgen Ziegler

Music listening and playlists datasetRoberto Turrin, Massimo Quadrana, Roberto Pagano, Paolo Cremonesi and Andrea Con-dorelli

Network-Based Extension of Multi-Relational Factorization ModelsRobin Burke

Next Basket Recommendation with Neural NetworksShengxian Wan, Yanyan Lan, Pengfei Wang, Jiafeng Guo, Jun Xu and Xueqi Cheng

Personality-Based Recommendations: Evidence from Amazon.comPanagiotis Adamopoulos and Vilma Todri

Recommendation with the Right Slice: Speeding Up Collaborative Filtering with Factoriza-tion MachinesBabak Loni, Martha Larson, Alexandros Karatzoglou and Alan Hanjalic

Recommendations to Enhance Children Web SearchesShahrzad Karimi and Maria Soledad Pera

Recommender Systems for Product BundlingMoran Beladev, Bracha Shapira and Lior Rokach

Style Recommendation for Fashion Items using Heterogeneous Information NetworkHanbit Lee and Sang-Goo Lee

Tackling Cold-Start Users in Recommender Systems with Indoor Positioning SystemsEmanuel Lacic, Dominik Kowald, Matthias Traub andElisabeth Lex

Towards Improving Top-N Recommendation by Generalization of SLIMSantiago Larrain, Denis Parra and Alvaro Soto

Word Embedding Techniques for Content-based Recommender Systems: an Empirical EvaluationCataldo Musto, Giovanni Semeraro, Marco De Gemmis and Pasquale Lops

Posters

Poster Area


Posters are exhibited in the desig-nated poster area

Poster/Demo Session



30 31

LocalRec: Workshop on Location-Aware Recommen-dations

The amount of available geo-referenced data has seen a dramatic explo-sion over the past few years. Human activities generate data and traces that are now often transparently annotated with location and contextual information. At the same time, it has become easier than ever to collect and combine rich and diverse information about locations. Exploiting this torrent of geo-referenced data requires bringing together scholars and practitioners from various research communities, and provides a tre-mendous potential to materially improve existing and offer novel types of recommendation services.

Panagiotis Bouros Humboldt-Universität zu Berlin, Germany

Neal LathiaUniversity of Cambridge, UK

Matthias RenzLudwig-Maximilians-Universität Munich, Germany

Francesco Ricci

Free University of Bozen-Bolzano, Italy

Dimitris Sacharidis TU Wien, Austria

Saturday Sept 19, 09:00 - 12:30, HS 5

Workshops Workshops

EMPIRE: 3rd Workshop on Emotions and Personality in Personalized Systems

The RecSys research community has done a tremendous job in the last decade on exploiting various data sources to improve recommendations of all kind through sophisticated algorithms. The workshop comple-ments these core RecSys activities by pushing the agenda of taking into account user-centric aspects, such as emotions and personality, into the RecSys framework. In fact, personality and emotions shape our daily lives by having a strong influence on our preferences, decisions and behav-iour in general. In recent years, emotions and personality have shown to play an important role in various aspects of recommender systems, such as implicit feedback, contextual information, affective content labeling, cold-start problem, diversity, cross-domain recommendations, group recommendations etc. With the development of robust techniques for the unobtrusive acquisition of emotions and personality the time is right to take advantage of these possibilities to collect massive datasets and improve recommender systems.

Marko TkalcicJohannes Kepler University, Austria

Berardina DeCarolisUniversity Aldo Moro Bari, Italy

Marco de GemmisUniversity Aldo Moro Bari, Italy

Ante OdicOutfit7 (Slovenian subsidiary Ekipa2 d.o.o.), Slovenia

Andrej Kosir University of Ljubljana, Slovenia

Saturday Sept 19, 09:00 - 12:30, HS 4

Tsvi KuflikWorkshop Co-Chair

Alan SaidWorkshop Co-Chair

32 33

Workshops Workshops

IntRS: Workshop on Interfaces and Human Decision Making for Recommender Systems

As an interactive intelligent system, recommender systems are developed to suggest items that match users’ preferences. Since the emergence of recommender systems, a large majority of research has focused on ob-jective accuracy criteria and less attention has been paid to how users interact with the system and the efficacy of interface designs from us-ers’ perspectives. The field has reached a point where it is ready to look beyond algorithms, into users’ interactions, decision making processes, and overall experience.

John O’Donovan University of California, Santa Barbara, USA

Nava TintarevUniversity of Aberdeen, UK

Alexander FelfernigGraz University of Technology, Austria

Peter BrusilovskyUniversity of Pittsburgh, USA

Giovanni Semeraro University of Bari Aldo Moro, Italy

Pasquale LopsUniversity of Bari Aldo Moro, Italy

Saturday Sept 19, 09:00 - 17:30, HS 3

CrowdRec: Workshop on Crowdsourcing and Hu-man Computation for Recommender Systems

The CrowdRec 2015 workshop is devoted to crowdsourcing and human computation for recommender systems. This workshop is the third in a series of workshops whose mission is to provide the RecSys community with a forum for the discussion of crowd-related topics. The aim of the workshop is to support the community in making full and equitable use of the power of the crowd. This power has the potential to not only im-prove recommender systems, but also to make possible applications and services not otherwise imaginable.

Martha LarsonDelft University of Technology, Nether-lands

Domonkos TikkGravity R&D, Hungary

Roberto TurrinContentWise R&D, Italy

Saturday Sept 19, 14:00 - 17:30, HS 5

34 35

Workshops WorkshopsSaturday Sept 19, 09:00 - 17:30, HS 7

RecSysTV: 2nd Workshop on Recommendation Sys-tems for Television and Online Video

For many households TV is still the central entertainment hub in their home, and the average TV viewer spends about half of his/her leisure time in front of a TV. The choice of what to watch becomes more over-whelming though because the entertainment options are scattered across various channels, such as on-demand video, digital recorders (on prem-ise or in the cloud) and the traditional linear TV. In addition, consumers can also access the content not just on the big screen, but also on their computers, phones, and tablet devices. Recommendation systems pro-vide TV users with suggestions about both online video-on-demand and broadcast content and help them to search and browse intelligently for content that is relevant to them. However, Recommendation systems for broadcast content still experience a number of challenges due to the peculiarity of such domain. For example, the content available on line-ar channels is constantly changing and often only available once which leads to severe cold start problems and we often consume TV in groups of varying compositions (household vs individual) which makes building taste profiles and modeling consumer behavior challenging.

Jan NeumannComcast Labs, USA

John HannonBoxfish, USA

Roberto TurrinContentWise R&D, Italy

Danny BicksonDato Inc., USA

Hassan SayyadiComcast Labs, USA

Sunday Sept 20, 09:00 - 12:30, HS 4

INRA: 3rd International Workshop on News Recom-mendation and Analytics

The 3rd International Workshop on News Recommendation and Analyt-ics (INRA 2015) addresses primarily news recommender systems and news analytics, with a focus on user profiling and techniques for dealing with and extracting knowledge from large-scale news streams. The news streams may originate in large media companies, but may also come from social sites, where user models are needed to decide how user-generat-ed content is to be taken into account. This workshop aims to create an interdisciplinary community that addresses design issues in news recom-mender systems and news analytics, and promote fruitful collaboration opportunities between researchers, media companies and practitioners.

Jon Atle GullaNTNU, Norway

Bei YuSyracuse University, USA

CBRecSys: 2nd Workshop on New Trends in Con-tent-Based Recommender Systems

The CBRecSys 2015 workshop aims to address this by providing a dedi-cated venue for papers dedicated to all aspects of content-based recom-mendation. This includes both recommendation in domains where textual content is abundant (e.g. books, news, scientific articles, jobs, educa-tional resources, Web pages) as well as dedicated comparisons of con-tent-based techniques with collaborative filtering in different domains. Other relevant topics related to content-based recommendations include opinion mining for text/book recommendation, semantic recommenda-tion, content-based recommendation to alleviate cold-start problems, as well as serendipity, diversity and cross-domain recommendation.

Toine BogersAalborg University Copenhagen, Denmark

Marijn KoolenUniversity of Amsterdam, Netherlands

Sunday Sept 20, 09:00 - 17:30, HS 6

36 37

WorkshopsSunday Sept 20, 09:00 - 17:30, HS 5

LSRS: Workshop on Large-Scale Recommender Systems

This workshop focuses on practical challenges of large scale recommend-er systems and their solutions. Our workshop combines together indus-try leaders with top researchers from academia. In the previous years our workshop attracted the largest number of participants relative to all the RecSys workshops. The workshop is jointly organized by Pandora, Dato, University of the Aegean and the Hungarian Academy of Science.

Tao Ye Pandora Inc., USA

Danny BicksonDato Inc., USA

Nicholas AmpazisUniversity of the Aegean, Greece

Andras BenczurInstitute for Computer Science & Control, Hungarian Academy of Sciences, Hungary

TouRS15: Workshop on Tourism Recommender Systems

Tourism is a very challenging field, ripe for the application of Recom-mender Systems. Travellers are very keen on using tools that may support their decision making processes when they are planning a trip, including the choice of destination, the selection of attractions to visit or the con-struction of a multi day plan. This workshop looks for contributions that explore the application of the latest recommendation techniques in this area, including aspects such as the discovery and management of indi-vidual and group preferences, the exploitation of user generated content, the trade off between accuracy and diversity, the use of Web based and mobile interfaces and planners, the semantic management of domain in-formation and user preferences, consideration of contextual factors, etc.

Antonio MorenoUniv. Rovira i Virgili, Spain

Laura SebastiáTechnical University of Valencia, Spain

Pieter VansteenwegenKU Leuven, Belgium

Sunday Sept 20, 09:00 - 17:30, HS 7

A Hybrid Recommendation System Based on Human CuriosityAlan Menk dos Santos

Context-aware Preference Modeling with Factorization Balász Hidasi

Exploring Statistical Language Models for Recommender SystemsDaniel Valcarce

Factorization Machines for Hybrid Recommendation Systems Based on Behavioral, Product, and Customer Data Stijn Geuens

Latent Context-Aware Recommender SystemsMoshe Unger

Listener-Inspired Automated Music Playlist GenerationAndreu Vall

Online Recommender Systems based on Data Stream Management Sys-tems Cornelius A. Ludmann

Doctoral SymposiumSaturday Sept 19, 09:00 - 17:30, SEM 101A

Dietmar JannachDoctoral Symposium Co-Chair

Gedas AdomaviciusDoctoral Symposium Co-Chair

38 39

Information for Presenters, Session Chairs & Participants

Each accepted full paper has a time allocation of thirty minutes. This includes time for setup and for questions, so presenters should consider speaking for 20 minutes, with 10 minutes discussion.

In the main session rooms (HS 1, HS 5) a laptop running Windows 7 is pro-vided. The laptops will support Powerpoint 2013 and PDF, and there will be Internet access available via the wireless network.

If you are chairing a session, please ensure to be at your room at least 10 minutes prior to the session starting.

If you are presenting in a session, please ensure that you turn up to your room at least 5—10 minutes prior the session starting and introduce yourself to the session chair. If you are using your own laptop for the presentation, then please turn up at least 10 minutes prior the session starting. If you are using the provided laptop, please transfer your presentation to the laptop prior the session start.

The Student Volunteers will be around the rooms before and during the ses-sion to assist if there are any problems, or to communicate any concerns to the organising committee.

Wireless network

Conference attendees are welcome to access the Internet via a wireless net-work provided by the TU Wien. The wireless network will be accessible within the conference rooms and corridors. Each attendee will receive an individual access code at the reception desk. There will be desk and power points for your laptops inside the conference rooms.

Catering

We provide morning coffee, lunch and afternoon coffee throughout the event. Coffee will be served at different stations in the TU Freihaus building. The lunch will take place in the TU Freihaus Mensa.

Sightseeing

If you would like to do some sightseeing, have a look at http://recsys.acm.org/recsys15/about-vienna/

InformationGENERAL CO-CHAIRSHannes Werthner, TU Wien, Austria

Markus Zanker, Alpen-Adria-Universität Kla-genfurt, Austria

PROGRAM CO-CHAIRSJennifer Golbeck, University of Maryland, USA

Giovanni Semeraro, University of Bari, Italy

POSTER AND DEMO CHAIRPablo Castells, Universidad Autónoma de Madrid, Spain

WORKSHOP CO-CHAIRSTsvi Kuflik, University of Haifa, Isreal

Alan Said, Recorded Future, Sweden

TUTORIAL CO-CHAIRSFrancesco Ricci, Free Univ. of Bozen-Bolzano, Italy

Alexander Tuzhilin, NYU, USA

DOCTORIAL SYMPOSIUM CO-CHAIRSGedas Adomavicius, Univ. of Minnesota, USA

Dietmar Jannach, TU Dortmund, Germany

PROCEEDINGS CHAIRMarco de Gemmis, University of Bari, Italy

PUBLICITY CO-CHAIRSPasquale Lops, University of Bari, Italy

Alexandros Karatzoglou, Telefonica Research, Spain

INDUSTRY CO-CHAIRSWerner Geyer, IBM Research, USA

Domonkos Tikk, Gravity R&D, Hungary

TREASURERNatascha Zachs, TU Wien, Austria

LOCAL ARRANGEMENTS AND STU-DENT VOLUNTEER CO-CHAIRSMarion Scholz, TU Wien, Austria

Christoph Grün, TU Wien, Austria

WEB CHAIRBenedikt Loepp, University of Duisburg-Essen, Germany

SENIOR PROGRAM COMMITTEEGediminas Adomavicius, University of Minnesota

Xavier Amatriain, Netflix

Shlomo Berkovsky, NICTA

Peter Brusilovsky, University of Pittsburgh

Robin Burke, DePaul University

Iván Cantador, Universidad Autónoma de Madrid

Pablo Castells, Universidad Autónoma de Madrid

Li Chen, Hong Kong Baptist University

Paolo Cremonesi, Politecnico di Milano

Marco De Gemmis, University of Bari

Martin Ester, Simon Fraser University

Boi Faltings, EPFL

Alexander Felfernig, Graz University of Technology

Jill Freyne, CSIRO

Werner Geyer, IBM T.J. Watson Research

Ido Guy, Yahoo! Israel

Alan Hanjalic, TU Delft

Dietmar Jannach, TU Dortmund

Alexandros Karatzoglou, Telefonica Re-search

George Karypis, University of Minnesota

Alfred Kobsa, Univ. of California, Irvine

Yehuda Koren, Google

Pasquale Lops, University of Bari

Bamshad Mobasher, DePaul University

Wolfgang Nejdl, L3S and University of Hannover

Pearl Pu, Swiss Federal Institute of Tech-nology

Francesco Ricci, Free Univ. of Bozen

Lior Rokach, BGU

Lars Schmidt-Thieme, Univ. of Hildesheim

Bracha Shapira, Ben-Gurion University

Harald Steck, Netflix

Domonkos Tikk, Gravity

Alexander Tuzhilin, Stern School of Busi-ness, New York University

Yong Yu, Shanghai Jiao Tong University

Organization

40 41

OrganizationLinas Baltrunas, Telefónica I+D, Spain

Alejandro Bellogín, Universidad Autónoma de Madrid, Spain

Shlomo Berkovsky, CSIRO, Australia

Roi Blanco, Yahoo Labs, UK

Fidel Cacheda, Universidad de A Coruña, Spain

Iván Cantador, Universidad Autónoma de Madrid, Spain

Òscar Celma, Pandora, USA

Elizabeth Daly, IBM, Ireland

Simon Dooms, Ghent University, Belgium

David Elsweiler, University of Regensburg, Germany

Zeno Gartner, Nokia, Germany

Bart Knijnenburg, University of California, Irvine, USA

Cataldo Musto, University of Bari, Italy

Vito Ostuni, Pandora, USA

Javier Parapar, Universidad de A Coruña, Spain

Denis Parra, Catholic University of Chile, Chile

Luiz Augusto Pizzato, 1-Page, Australia

Francesco Ricci, Free University of Bozen-Bolzano, Italy

Rodrygo Santos, Universidade Federal de Minas Gerais, Brazil

Yue Shi, Yahoo Labs, Netherlands

Marko Tkalcic, Johannes Kepler University Linz, Austria

Michele Trevisiol, Yahoo Labs, UK

David Vallet, Google, Australia

Saúl Vargas, University of Glasgow, UK

Dell Zhang, Birkbeck University of London, UK

POSTER PROGRAM COMMITTEE

OrganizationREGULAR PROGRAM COMMITTEEAmr Ahmed, Google Research

Jussara Almeida, UFMG

Sarabjot Anand, Algorithmic Insight

Linas Baltrunas, Telefonica Research

Alejandro Bellogin, Universidad Autonoma de Madrid

Maria Bielikova, Slovak Univ. of Technology in Bratislava

Derek Bridge, University College Cork

Sylvain Castagnos, LORIA

Enhong Chen, Univ. of Science & Technology of China

Maurice Coyle, Heystaks

Elizabeth M. Daly, IBM Research

Ernesto William De Luca, Potsdam University of Applied Sciences

Toon De Pessemier, Ghent University

Arjen de Vries, CWI

Tommaso Di Noia, Politecnico di Bari

Ernesto Diaz-Aviles, IBM Reseach

Simon Dooms, Ghent University

Hendrik Drachsler, Open University of the Netherlands

Gideon Dror, The Academic College of Tel-Aviv-Yaffo

Casey Dugan, IBM T.J. Watson Research

Michael Ekstrand, Texas State University

Abdulmotaleb El-Saddik, University of Ottawa

Zeno Gantner, Nokia gate5 GmbH

Florent Garcin, EPFL

Franca Garzotto, Politecnico di Milano

Yong Ge, University of North Carolina at Charlotte

Fatih Gedikli, adesso AG

Marcos Goncalves, Federal University of Minas Gerais

Derek Greene, University College Dublin

Jiawei Han, University of Illinois at Urbana-Champaign

Frank Hopfgartner, University of Glasgow

Andreas Hotho, University of Wuerzburg

Rong Hu, Swiss Federal Institute of Technology

Neil Hurley, University College Dublin

Alejandro Jaimes, Yahoo! Research

Mohsen Jamali, WalmartLabs

Robert Jäschke, L3S Research Center

Yexi Jiang, Florida International University

Bart Knijnenburg, University of California, Irvine

Noam Koenigstein, Microsoft R&D

Tsvi Kuflik, The University of Haifa

Paul Lamere, The Echo Nest

Martha Larson, Delft University of Technology

Neal Lathia, University of Cambridge

Sangkeun Lee, Oak Ridge National Laboratory

Sang-Goo Lee, Seoul National University

Lei Li, Florida International University

Tao Li, Florida International University

Qi Liu, University of Science and Technology of China

Huan Liu, Arizona State University

Bernd Ludwig, Universität Regensburg

Luc Martens, Ghent University

Judith Masthoff, University of Aberdeen

Kevin Mccarthy, University College Dublin

Wagner Meira Jr., Universidade Federal de Minas Gerais

Cataldo Musto, University of Bari

Nathan Nan Liu, Yahoo! Labs

Alexandros Nanopoulos, University of Eichstätt-Ingolstadt

Fedelucio Narducci, University of Bari

Yiu-Kai Ng, Brigham Young University

John O’Donovan, University of California Santa Barbara

Nuria Oliver, Telefonica Research

Michael O’Mahony, University College Dublin

Balaji Padmanabhan, University of South Florida

Rong Pan, Sun Yat-sen University

Ulrich Paquet, Microsoft

Maria Soledad Pera, Brigham Young University

Till Plumbaum, Technische Universität Berlin

Daniele Quercia, Yahoo! Labs

Rachael Rafter, University College Dublin

Steffen Rendle, Google

Inbal Ronen, IBM Haifa Research Lab

Alan Said, Recorded Future

Olga C. Santos, aDeNu Research Group (UNED)

Rodrygo Santos, Universidade Federal de Minas Gerais

Markus Schaal, University College Dublin

Shilad Sen, Macalester College

Guy Shani, Ben Gurion University

Yue Shi, Yahoo! Labs

Fabrizio Silvestri, Yahoo! Labs

Neel Sundaresan, eBay

Panagiotis Symeonidis, Aristotle Univ. of Thessaloniki

Nava Tintarev, University of Aberdeen

Mitul Tiwari, LinkedIn

Roberto Turrin, Moviri

Nicolas Usunier, Université Technologique de Compiègne

Jian Wang, LinkedIn

Jun Wang, University College London

Martijn Willemsen, Eindhoven University of Technology

David Wilson, University of North Carolina at Charlotte

Hui Xiong, Rutgers University

Guandong Xu, University of Technology Sydney

Kalina Yacef, The University of Sydney

Quan Yuan, Alibaba Group

Jie Zhang, Nanyang Technological University

Tingshao Zhu, Chinese Academy of Sciences

Nivio Ziviani, Federal University of Minas Gerais

42 43

Doctoral Symposium Dinner @ AugustinerkellerTuesday Sept 15, 19:00 - 22:00

The Augustinerkeller restaurant is one of the last ancient monastery cellars in Vienna’s his-toric city center. The splendid ancient vaulting of the cellar has been well preserved through-out the centuries and can still be seen. It was part of the former fortifications and only in 1924 it was changed into a restaurant.

Since 1954 the restaurant has been run by the family Bitzinger, and today the third genera-tion is working tirelessly to cultivate and main-tain the tradition of Viennese hospitality.

Enjoy the Viennese cuisine as well as seasonal specialties together with excellent vines from the restaurants own wine cellars and the re-freshing private brand draft beer “Opernbräu”. Traditional live music is played every evening and thus complements the authentic Viennese experience at this historic place situated right in the heart of Vienna.

The Augustinerkeller can easily be reached from the underground stations Stephansplatz (U1, U3) or Karlsplatz (U1, U2, U4) via a short walk.

Location

Augustinerstraße 1

Web

http://www.bitzinger.at/augustinerkeller

© Mapbox © OpenStreetMap


EventsVienna, the capital of Austria, is a city of over 1.8 million inhabitants. It is in high demand as destination for conferences and conventions as it is easy to reach, has plenty to offer and is considered one of the safest cities offering the highest standard for quality of living (no. 1 according to the Worldwide Quality of Living Survey 2015, Mercer Human Resource Consulting).

All the year round, Vienna is a leading tour-ism destination for its historic city with nu-merous cultural attractions like museums, opera houses, concert halls, theatres, and pastry indulgence. For those who are inter-ested in culinary indulgence, Vienna is well known for its coffee culture at impressive imperial cafés and its “Heurigen” places (wine tasting of local wines at local vine-yards surrounding the city).

Vienna has a long academic history with 9 universities and almost 200.000 students; it hosts major international organizations such as the UN, UNIDO, IAEA, OECD and OPEC. Furthermore, it is a hub for Eastern Europe, with many already historic rela-tionships. More than 300 international corporations run their eastern European headquarters in Vienna. Thus, the Vienna airport is an international hub and conven-iently close to the city (16 minutes by train to the city center).

Must sees in Vienna:

» Schönbrunn Palace

» St. Stephen‘s Cathedral

» Vienna Hofburg (Palace)

» Belvedere Palace

» Vienna Ferris Wheel

» Imperial Treasury

» Museum of Art History

About Vienna

44 45

EventsConference Dinner @ Vienna City HallThursday Sept 17, 19:15 - 22:00

The dinner takes place at the Vienna City Hall (Rathaus Wien). The City Hall is one of the most splendid amongst the numerous monu-mental buildings in Vienna. Designed by Frie-drich Schmidt (1825 - 1891), it was erected between 1872 and 1883.

The architecture of the Ringstraße is domi-nated by historicism. In Historicism various stylistic elements of the past were combined into a style in its own right. Friedrich Schmidt however orientated himself on one particular period. The City Hall was built in gothic style, with a tower similar to gothic cathedrals. The gothic era saw the growth of the cities and the emergence of an urban burgeoisie.

Today the City Hall is the head office of Vi-enna‘s municipal administration. More than 2000 people work in this building.

The Vienna City Hall can easily be reached from the conference venue via Subway U2 (purple line) - Station Rathaus.

The dinner speech is given by Swaminathan Vishwanathan (Principal Research Scientist in Amazon’s Personalization Team and Professor in Computer Science at UCSC).

Location

Lichtenfelsgasse, Entrance Stairs I

Web

http://www.wienerrathaus.at


EventsConference Reception @ TU Wien, PrechtlsaalWednesday Sept 16, 19:00 - 22:00

The reception takes place in the Prechtl-saal of the main building of the TU Wien.

In 2015, the TU Wien celebrates 200 years of existence. Founded in 1815 as the „Im-perial-Royal Polytechnic Institute“, it cur-rently has about 27,900 students.

Location

Karlsplatz 13

Web

http://www.tuwien.ac.at



Conference Venue

Conference Reception

Doctoral Symposium Dinner

Conference Dinner

Steering Committee Dinner

© basemap.at

Venue Information

TU Wien, FreihausWiedner Hauptstraße 81040 ViennaAustria

POWERED BY

SPECIAL SUPPORTERS

GOLD SUPPORTERS

DIAMOND SUPPORTER

PLATINUM SUPPORTERS

SILVER SUPPORTER

Recommender Systems - RecSysrecsys.acm.org/wp-content/uploads/2015/08/RecSys... · the submitted...

Documents

Transcript of Recommender Systems - RecSysrecsys.acm.org/wp-content/uploads/2015/08/RecSys... · the submitted...