Projection: A Mixed-Initiative Research Process
This addresses the problem of opaque machine learning systems for researchers and users seeking better insight and control in information retrieval, though it appears incremental as it builds on existing visualization and clustering techniques.
The paper tackles the low-bandwidth communication between humans and machines in search and recommender systems by introducing Projection, a mixed-initiative interface that enhances the research process through contextual searches and multi-dimensional visualizations, with interest shown from potential customers.
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.