Projection: A Mixed-Initiative Research Process

TL;DR

Projection is a mixed-initiative interface designed to enhance communication between humans and machine learning systems by supporting hierarchical structuring and multi-dimensional visualization of research data.

Contribution

It introduces a novel interface that facilitates richer interaction and understanding in research workflows through visualization and hierarchical organization.

Findings

Potential users are interested in integrating their research outlining and search processes.

The interface helps structure searches in hierarchies.

It enables visualization of related knowledge spaces.

Abstract

Communication of dense information between humans and machines is relatively low bandwidth. Many modern search and recommender systems operate as machine learning black boxes, giving little insight as to how they represent information or why they take certain actions. We present Projection, a mixed-initiative interface that aims to increase the bandwidth of communication between humans and machines throughout the research process. The interface supports adding context to searches and visualizing information in multiple dimensions with techniques such as hierarchical clustering and spatial projections. Potential customers have shown interest in the application integrating their research outlining and search processes, enabling them to structure their searches in hierarchies, and helping them visualize related spaces of knowledge.