Quantifying the Presence of Phone Users

Abstract

-Presence-enabled telephony services can reduce telephone tag and improve customer satisfaction. In this paper we proposed the Bayesian inference model to calculate the willingness level of the callee to accept calls. Before making a call, the caller may use the willingness calculator to find out whether the callee is available. Based on this level the user can make a decision whether to make a call. For validation of our results, we used actual call logs of 100 users collected at MIT by the Reality Mining Project group for a period of 8 months. We used time of the day, day of the week, talk-time and location for calculating the willingness level. Our results show a good agreement between computed willingness level and the number of missed/rejected calls. This service can be included as part of the presence server. When deployed, this service can increase productivity, avoid unwanted calls and reduce the call traffic congestion. This service is beneficial to both subscribers and phone service providers. However, in order to make this service a reality, we need to take into account other factors such social closeness, proximity, multiplexity and reputation of the caller. *

Modeling Users’ Behavior from Large Scale Smartphone Data Collection

“…Husna et al [14] and Zhang and Dantu [30] availability for phone calls. They used 3 basic features such as time of the day, day of the week and location, and predicted the user's availability and likelihood of accepting phone calls based on a weighted average of these feature values.…”