EntityBot: Actionable Entity Recommendations for Everyday Digital Task

Abstract

Our everyday digital tasks require access to information from a wide range of applications and systems. Although traditional search systems can help find information, they usually operate within one application (e.g., email client or web browser) and require the user's cognitive effort and attention to formulate proper search queries. In this paper, we demonstrate EntityBot, a system that proactively provides useful and supporting entities across application boundaries without requiring explicit query formulation. Our methodology is to exploit the context from screen frames captured every 2 seconds to recommend relevant entities for the current task. Recommendations are not restricted to only documents but include various kinds of entities, such as applications, documents, contact persons, and keywords representing the tasks. Recommendations are actionable, that is, a user can perform actions on recommended entities, such as opening documents and applications. The EntityBot also includes support for interactivity, allowing the user to affect the recommendations by providing explicit feedback on the entities. The usefulness of entity recommendations and their impact on user behavior has been evaluated in a user study based on real-world tasks. Quantitative and qualitative results suggest that the system had an actual impact on the tasks and led to high user satisfaction.