2012 Poster Sessions : A Platform for Large Scale Machine Learning on Web Design

Student Name : Arvind Satyanarayan
Advisor : Scott Klemmer
Research Areas: Graphics/HCI
The Web is an enormous and diverse repository of design examples. Although people often draw from extant designs to create new ones, existing Web design tools do not facilitate example reuse in a way that captures the scale and diversity of the Web. To do so requires using machine learning techniques to train computational models which can be queried during the design process. In this work-in-progress, we present a platform necessary for doing such large-scale machine learning on Web designs, which consists of a Web crawler and proxy server to harvest and store a lossless and immutable snapshot of the Web; a page segmenter that codifes a page's visual layout; and an interface for augmenting the segmentations with crowdsourced metadata.

Arvind Satyanarayan is a first year PhD student in the HCI group. At Stanford, he has been working with Professor Scott Klemmer's group on building a platform to support large-scale machine learning on web designs, and with Professor Jeffrey Heer on methods to facilitate storytelling through online browser-based interactive data visualizations. As an undergraduate at UC San Diego, Arvind was advised by Professor Jim Hollan and investigated interaction techniques to support multi-user collaborative work with large display walls.