Svetlin Alex Bostandjiev

Google Chrome 3D Web Browsing
At Google, I worked on Chrome and built an Extensions API that allows for interacting with multiple web pages on screen at the same time. Example applications might look like Safari’s “Top Sites” or Chrome’s “Most Visited” page augmented with real-time display updates and user interaction. In combination with WebGL and its texture capabilities the API could be used to create true 3D browser environments on the web!

TasteWeights: Visual Hybrid Recommendations
My current work at the University of California, Sanata Barbara focuses on visual interactive recommender systems. We investigate how to engage the user in interactions with the recommendation process in order to improve their satisfaction and accuracy of the recommender system.

I am working on a hybrid system designed to personalize information flow from multiple social and semantic web resources such as Wikipedia, Facebook, and Twitter. The system employs hybrid techniques from traditional recommender system literature, in addition to a novel interactive interface which serves to explain the recommendation process and elicit hybridization preferences from the end user.

WiGis: Web-based Graph Visualization
WiGis is an open-source framework for large-scale graph visualization on the Web. At UCSB, I invented a technique enabling interaction with graphs of over a million nodes in the browser. WiGis is used by US National Intelligence, US Army, IARPA, and NSA.

SmallWorlds: Visual Collaborative Filtering Recommendations
Previously, we developed SmallWorlds, a visual interactive interface that allows users to specify, refine, and build item-preference profiles. The interface facilitates expressions of taste through simple graph interactions and these preferences are used to compute personalized, fully transparent item recommendations for a target user. Predictions are based on a collaborative analysis of preference data from a user’s direct friend group on a social network.

WiGipedia: Visual Editing of Wikipedia
WiGipedia is an interactive graph visualization embedded in every Wikipedia article where graph entities represent articles and categories with typed edges between them. This intelligent web interface is designed to both inform the user of interesting contextual information pertaining to the current article, and to provide a simple way to introduce and/or repair semantic relations between wiki articles. User actions result in improved accuracy and consistency of structured data spread across multiple articles. WiGipedia provides users with an intuitive interface that allows single-click Wikipedia edits without knowledge of the Wikipedia markup language, templates, etc.