User Group Analytics: Discovery, Exploration and Visualization
Half-day tutorial
Time: Friday, 26 October 2018, 08:15AM-09:45AM & 10:15AM-11:45AMRoom: Varsavia
Behrooz Omidvar-Tehrani
University of Grenoble Alpes, France
Behrooz Omidvar-Tehrani is a postdoctoral researcher in the University of Grenoble Alpes, France. Previously, he was a post-doctoral researcher at the Ohio State University, USA. His research is in the area of data management, focusing on interactive analysis of user data. Behrooz received his PhD in Computer Science from University of Grenoble Alpes, France. He has published in several international conferences and journals including CIKM, ICDE, VLDB, EDBT and KAIS. Also, he has been a reviewer for several conferences and journals including Information Systems, TKDE, DAMI, CIKM, ICDE, and AAAI.
Sihem Amer-Yahia
Laboratoire d’Informatique de Grenoble, CNRS, France
Sihem Amer-Yahia is a Research Director at LIG in Grenoble where she leads the SLIDE team. Her interests are at the intersection of large-scale data management and user data exploration. Before joining CNRS, she was Principal Scientist at QCRI, Senior Scientist at Yahoo! Research and Member of Technical Staff at AT&T Labs. Sihem served on the SIGMOD Executive Board, the VLDB Endowment, and the EDBT Board. She is the Editor-in-Chief of the VLDB Journal and has been on the editorial boards of TODS and the Information Systems Journal. She is chairing VLDB 2018 and WWW Tutorials 2018 and will be chairing ICDE Tutorials 2019 and WWW Workshops 2019. Sihem received her Ph.D. in CS from Paris-Orsay and INRIA in 1999, and her Diplôme d’Ingénieur from INI, Algeria.
Abstract
User data is becoming increasingly available in various domains from the social Web to patient health records. User data is characterized by a combination of demographics (e.g., age, gender, occupation) and user actions (e.g., rating a movie, following a diet). Domain experts rely on user data to conduct large-scale population studies. Information consumers rely on the social Web for routine tasks such as finding a book club. User data analytics is usually based on identifying group-level behaviors such as “countryside teachers who watch Woody Allen movies.” User Group Analytics (UGA) addresses peculiarities of user data such as noise and sparsity. This tutorial reviews research on UGA and discusses different approaches and open challenges for group discovery, exploration, and visualization.
Detailed Outline
What is user data and user groups?
Real use cases in various application domains such as advertisement, program committee formation and quantified-self
Overview of UGA challenges
User group exploration: defining the group exploration process, and categorizing related work into by-query, by-facet, by-example, and by-analytics exploration
User group visualization: defining the building blocks of group visualization and mapping functions, and categorizing related work into graph-based and map-based visualization
Discussion of approaches for combining discovery and visualization in the following categories: distribution-based, facet-based, relation-based, and time-based
Discussion of visualization approaches for representing discovered groups, such as self-organizing maps, belt charts, and regression heatmaps
Discussion of approaches for combining discovery and exploration
Discussion of different approaches of explicit and implicit feedback capture to enable exploratory discovery
Discussion of approaches for combining exploration and visualization (aka, Visual Analytics)
Challenges of integrating UGA components
Discussion of recently established literature of all-in-one UGA
Discussion of future directions towards a full-fledged integration