Logo Logo
Help
Contact
Switch Language to German
Dingler, Tilman; Tag, Benjamin; Lehrer, Sabrina; Schmidt, Albrecht ORCID: 0000-0003-3890-1990 (2018): Reading Scheduler: Proactive Recommendations to Help Users Cope with Their Daily Reading Volume. In: 17Th International Conference on Mobile and Ubiquitous Multimedia (Mum 2018): pp. 239-244
Full text not available from 'Open Access LMU'.

Abstract

To help deal with daily reading volumes, we present Reading Scheduler, a smartphone application linked to people's reading list, which triggers reading reminders throughout the day. The app suggests articles according to their length, complexity, and the time available for reading as indicated by the user. In a field study, we collected usage data from ten participants over the course of two weeks. During this time, we recorded mobile sensor data and trained a classifier to detect opportune moments for reading. Participants read 182 articles while we collected 787,752 sensor data points. Together with an assessment of the feasibility of proactive reading suggestions, we present a prediction model with close to 73% accuracy, that can be used to build mobile recommender systems for utilizing idle moments for reading throughout the user's day.