Augur: Mining Human Behaviors from Fiction to Power Interactive Systems

TL;DR

This paper introduces Augur, a knowledge base mined from fiction that enables systems to predict human activities and adapt behaviors, improving human-computer interaction without manual programming.

Contribution

Augur demonstrates how analyzing over one billion words of fiction can create a broad, predictive knowledge base for human activities, advancing interactive system capabilities.

Findings

Achieved 96% recall and 71% precision in activity prediction

94% of predictions rated sensible by human judges

Enabled systems to adapt behaviors based on predicted activities

Abstract

From smart homes that prepare coffee when we wake, to phones that know not to interrupt us during important conversations, our collective visions of HCI imagine a future in which computers understand a broad range of human behaviors. Today our systems fall short of these visions, however, because this range of behaviors is too large for designers or programmers to capture manually. In this paper, we instead demonstrate it is possible to mine a broad knowledge base of human behavior by analyzing more than one billion words of modern fiction. Our resulting knowledge base, Augur, trains vector models that can predict many thousands of user activities from surrounding objects in modern contexts: for example, whether a user may be eating food, meeting with a friend, or taking a selfie. Augur uses these predictions to identify actions that people commonly take on objects in the world and estimate a user's future activities given their current situation. We demonstrate Augur-powered, activity-based systems such as a phone that silences itself when the odds of you answering it are low, and a dynamic music player that adjusts to your present activity. A field deployment of an Augur-powered wearable camera resulted in 96% recall and 71% precision on its unsupervised predictions of common daily activities. A second evaluation where human judges rated the system's predictions over a broad set of input images found that 94% were rated sensible.