Workshop on Recommender Systems for a Massively Connected Society

November, 21st, 2014

Auditorium 3 – ICEx – UFMG

Goal

The goal of this workshop is to discuss the state-of-the-art in recommender systems, as well as future trends in a massively connected society where, beyond the internet, the web and the online social networks, there will all sorts of sensors and connected devices (“internet of things”).

Program

9:00 – 12:00

Tutorial: Mining Social Networks for Recommendation

by Martin Ester (Simon Fraser University, Canada)

With the emergence of online social networks, academia and industry have explored ways to exploit the information in social networks to improve the quality of recommendations and to support new recommendation tasks. The underlying motivation is to capture the effects that govern the evolution of social networks, i.e. social influence, selection, correlational influence and transitivity, to enhance the typically very sparse rating matrix. Recommender systems exploiting a social network promise to outperform traditional recommenders in particular for cold-start (new) users who have not yet provided enough information about their preferences. After introducing the motivation and some of the practical applications, we discuss social networks and the main factors affecting their evolution. We then review state-of-the-art methods for item recommendation in social networks, both memory-based approaches and model-based approaches, in particular matrix factorization. We discuss friend recommendation, an important recommendation task that is unique to the context of social networks. We conclude the tutorial with a discussion of future research directions such as privacy-preserving recommendations and social recommendation in distributed/peer-to-peer networks.

Outline

1. Introduction
2. Social networks and the effects that govern their evolution
3. Memory-based approaches for item recommendation in social networks
4. Model-based approaches for item recommendation in social networks
5. Friend recommendation
6. Future directions

This tutorial targets researchers who want to get up to speed in this emerging research area as well as practitioners who are interested in developing their own applications. The tutorial assumes familiarity with the common methods of recommender systems. Some background in data mining and social network analysis will be helpful, but is not required.

Bio

Martin Ester is Professor of Computing Science at Simon Fraser University in Burnaby, British Columbia. He got his Diplom (M.Sc.) in Computer Science from University of Dortmund, Germany, in 1984 and his Ph.D. in Computer Science from ETH Zurich, Switzerland, in 1990. He is the co-director of the Databases and Data Mining Laboratory and currently is the Director of the School of Computing Science.

13:00 – 15:00

Poster presentation: Recommender Systems Projects

UFMG students/Prof. Rodrygo Santos

15:00 – 17:00

Panel: Recommender Systems for a Massively Connected Society: Challenges and Trends

• Nivio Ziviani
• Martin Ester
• Antonio Loureiro