Context-aware Call Management for Mobile Phones

Author/Creator

Author/Creator ORCID

Date

2017-01-01

Department

Information Systems

Program

Information Systems

Citation of Original Publication

Rights

This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Distribution Rights granted to UMBC by the author.

Abstract

When a user receives a phone call, his mobile phone would notify him with a ringing sound or vibration immediately without considering whether or not the user is available to answer the call, which could be disruptive to his ongoing task or social situation. In addition, many incoming calls are unwanted for users. Although users may turn off their mobile phones in advance or just set their mobile phones in a silent mode to avoid interruptions, it would cause the problems of forcing an extra step for users, missing important phone calls, or forgetting to switch a phone back to the regular mode. Mobile call management is a type of mobile applications for coping with the problem of mobile interruption. A mobile call management system can sense context information about the situational environment of a user and choose appropriate mechanisms to handle incoming phone calls, making call management more effective, adaptive, and personalized. Existing mobile call management systems often utilize only one type of context information (e.g., location) for call management. In reality, however, mobile call management often needs diverse contextual information of individual users, such as time, location, event, and social relations. Another major challenge in mobile call management is to deal with noise and ambiguity of real-time data collected from multiple sensors embedded in mobile phones. The objective of this dissertations research is to develop a conceptual framework for mobile call management and design, implement, and empirically evaluate a novel mobile call management method called CaCM (Context-aware Call Management) that incorporates diverse context factors, including time, location, event, social relations, environment, body position, and body movement, and leverages machine learning algorithms to reduce mobile interruption and improve the effectiveness and user satisfaction with mobile call management. The results of an empirical evaluation via a field experiment indicate that CaCM shows advantages in the accuracy of interruptability prediction and user perceptions in comparison with existing context-aware mobile call management methods.