Learning usage behavior based on app feedback
|Erik Bager Beuschau|
|Abstract||As people spend more and more time with their smartphones, it is necessary to have a solid understanding of modern smartphone usersí behaviour in order to get a better indication of their needs in various situations and contexts.|
In this project, an Android application has been build which continuously collects data on the userís active application. This data is sent to a server, which has also been created during the project, and it is with background in this collected data that further analysis have been conducted. Some of these analysis have already been seen in other studies, while some are new to this area.
Some of the obtained results indicate a number of significant trends within usage behaviour, and they give a vital insight into how users navigate and operate within various contexts. For instance, a lot of games are used mostly around and after midnight, social applications (e.g. Twitter and Facebook) will most often be used right before a browser application, and it has been possible to detect similar usage behaviour within specific distinguishable geographical areas for single users. It has also been shown that more than 50% of usersí application usage is registered within a 500 metres radius.
|Type||Master's thesis [Academic thesis]|
|Publisher||Technical University of Denmark, DTU Informatics, E-mail: firstname.lastname@example.org|
|Address||Asmussens Alle, Building 305, DK-2800 Kgs. Lyngby, Denmark|
|Note||DTU supervisors: Jakob Eg Larsen and Michael Kai Petersen, DTU Informatics|
|BibTeX data|| [bibtex]|
|IMM Group(s)||Intelligent Signal Processing|
Back :: IMM Publications