Efficacy of mobile context-aware notification management systems: A systematic literature review and meta-analysis

Abstract

Abstract-Notifications can be relevant but they can also decrease productivity when delivered at the wrong point in time. Smartphones are increasingly capable of detecting relevant context information with the goal to decrease the number of these badly timed interruptions. Accordingly, research on contextaware notification management systems (CNMSs) on mobile devices has received increasing attention recently, prototypes have been built and empirically evaluated. However, there exists no systematic overview of mobile CNMSs evaluating their efficacy. The objectives of the current work are therefore to identify relevant empirical studies that have assessed the efficacy of mobile CNMSs and to discuss the findings with respect to future work. A systematic literature review and meta-analysis was conducted to address these objectives. Consistent with prior work, two efficacy metrics were applied: response rate and response delay. A keyword-based search strategy was used and resulted in 1'634 studies, out of which 8 were relevant for the topic. Findings indicate that mobile CNMSs increase the response rate, while there was only little evidence that they reduce response time, too. Implications for researchers and practitioners are discussed and future research is outlined that aims at further increasing the efficacy of mobile CNMSs.

Investigating Intervention Components and Exploring States of Receptivity for a Smartphone App to Promote Physical Activity: Protocol of a Microrandomized Trial

“…Drawing on previous literature on context-aware mobile notification management systems [58], we identified smartphone sensors that may aid with predicting the participants’ state of receptivity. Sensor data were obtained from participants during the intervention period.…”

“…First, we plan to evaluate the performance of supervised learning algorithms in predicting response rate and response time. These algorithms have produced predictions of acceptable accuracy in previous studies on interruptibility [58]. Second, we plan to frame the problem at hand as a classification problem.…”

Exploring the State-of-Receptivity for mHealth Interventions

“…Mehrotra et al identiied neuroticism and extroversion as discriminating features of how fast people respond to push notiications [22]. The results from all the above mentioned works, however, have not been generalizable: diferent studies report diferent and often conlicting results [19]. This could be because of small sample sizes, and homogeneity amongst the participants in a study, who usually belong to a similar demographic group, e.g., students or oice workers.…”

Investigating Intervention Components and Exploring States of Receptivity for a Smartphone App to Promote Physical Activity: Protocol of a Microrandomized Trial (Preprint)

“…Drawing on previous literature on context-aware mobile notification management systems [45], we identified smartphone sensors that may aid with predicting the participants' state of receptivity. Sensor data were obtained from participants during the intervention period.…”

“…First, we plan to evaluate the performance of supervised learning algorithms in predicting response rate and response time. These algorithms have produced predictions of acceptable accuracy in previous studies on interruptibility [45]. Second, we plan to frame the problem at hand as a classification problem.…”