Bayesphone: Precomputation of Context-Sensitive Policies for Inquiry and Action in Mobile Devices

Abstract

Abstract. Inference and decision making with probabilistic user models may be infeasible on portable devices such as cell phones. We highlight the opportunity for storing and using precomputed inferences about ideal actions for future situations, based on offline learning and reasoning with the user models. As a motivating example, we focus on the use precomputation of call-handling policies for cell phones. The methods hinge on the learning of Bayesian user models for predicting whether users will attend meetings on their calendar and the cost of being interrupted by incoming calls should a meeting be attended.

Breaking the habit: Measuring and predicting departures from routine in individual human mobility

“…The evaluation of cost is usually framed as the problem of inferring the interruptibility of a user (and assumes fixed value, or benefit, for each notification). For example, Iqbal and Bailey [19] and Horvitz et al [20] evaluate the interruption cost based on the user's current activity. When the cost is high, the mobile device should refrain from (or delay) alerting the user about phone calls, reminders, or more application-specific events.…”

User-Adapted Recommendation of Content on Mobile Devices Using Bayesian Networks

“…Recently, a Bayesian network [10] has drawn researchers' attention as a technique for user modeling [11]- [13]. A Bayesian network models uncertain phenomena, such as preferences and situations.…”

Conceptualizing Interpersonal Interruption Management: A Theoretical Framework and Research Program

“…Researchers adopting this paradigm addressed interruptibility by explicitly looking at individuals self reports on their perceptions of burden/cost [20][21], perceptions of value [24], willingness to be interrupted [18] and responsiveness to an interruption [2]. This definition of interruptibility in interpersonal communication is more fitting since how much it affects ones cognitive/social state, and how willing people are to allow it to affect their cognitive/social state, are two different things.…”

“…al. [20] evaluated real time willingness to be interrupted based on calendar information of meeting attendance and pre-defined user interruptibility levels. They allowed users to define callers interruption rights based on organizational relationships, activities, and ad hoc groups such as critical associates and close friends.…”

“…The value of an interruption has also been operationalized by a number of researchers in terms of its cost or burden [10][18] [20]. Ho and Intille [18] summarize value in terms of the burden with respect to various factors: activity of the user; utility of a message; emotional state of the user; modality and frequency of the interruption; task efficiency rate; users perceived authority on interruption, users previous and future activity; users social expectation; and history and likelihood of response.…”