Abstract:
The goal of visual analytics is to create a symbiosis between human and computer by leveraging their unique strengths. While this model has demonstrated immense success, we are yet to realize the full potential of such a human-computer partnership. In a perfect collaborative mixed-initiative system, the computer must possess skills for learning and anticipating the users’ needs. Addressing this gap, we propose a framework for inferring attention from passive observations of the user’s click, thereby allowing accurate predictions of future events. We demonstrate this technique with a crime map and found that users’ clicks can appear in our prediction set 92% – 97% of the time. Further analysis shows that we can achieve high prediction accuracy typically after three clicks. Altogether, we show that passive observations of interaction data can reveal valuable information that will allow the system to learn and anticipate future events.
Above, we see particles for each session in our study. Participants interacted with the map below and performed either Type-Based, Geo-Based, or Mixed tasks. For Type-Based tasks, they explored the same types of crime across the entire map. Geo-Based involved investigating different types of crime in a specific geographical region, and Mixed tasks consisted of the same types of crime, but constrained to a geographic region. The location and colors of the squares indicate the features of the observed click.
Each particle has three parameters: x/y-coordinate location, the ordinal type of the particle, and bias of the particle. We define the bias as a number in the range [0,1] where 0 indicates location certainty and 1 indicates type certainty. We map the bias values to the fill opacity of each circle. Therefore, an opaque circle indicates a particle with high type certainty and high location uncertainty, which in effect up-votes marks of the respective color across the entire map.