Social analytics: Learning from human interactions

ICML 2010 Workshop

25th June, 2010
Haifa, Israel


Call for Participation

Important Dates

Accepted papers


Invited Talks




Overview of the Workshop


Our social interactions are often made by electronic means, and are thus recorded in accessible formats. This opens a range of possibilities for studying human interactions from data such as social network sites on the web and cell phone communications. These tasks usually involve massive amount of data (billions of records) that is often quite noisy and even corrupted. Social and artificial networks suggest new challenges in modelling machine learning problems as there are strong spatial and temporal correlations. In this workshop we will hear researchers from academia and industry share their insights about the theory and applications of social analytics. Our focus will be on graph mining and predictive tools that can be used in this area. We will also consider different applications from recommender systems, marketing, search, network optimization and other emerging areas.

Background and Objectives

Social analytics is a new and exciting area of research, which has begun in earnest in the last decade, mainly due to the availability of data. Machine Learning is well suited to contribute to this field, which requires learning from large amounts of data in order to gain a better understanding, provide better predictions and ultimately change and adjust the network behavior.

Impact and Expected Outcome

Our goal is to bring people from different fields, ranging from computer science to marketing, from both academia and industry, to foster a discussion on the different approaches people have taken to the study of social phenomena. A successful workshop will introduce people to the tools and data available for social research in various communities. A primary goal of the workshop is to create a set of common theoretical problems to work on and to solicit data from companies to facilitate common research challenges.