Hide/Show Apps

Mobile user data mining to infer knowledge workers' differences in office environments for effective health delivery

Çavdar, Şeyma
Owing to the widespread and ubiquitous nature of mobile technologies, a large amount of data about users including location, access and interaction behavior is currently available. This data has recently become important as it has the potential to reveal personal information, social context and user characteristics, which can be significant for effective health interventions through mobile phones. Accordingly, this thesis mainly aims to explore the individual differences of knowledge workers and social context in order to infer their available moments using mobile sensor data. A hybrid personalized model is presented as a novel approach for this purpose. Based on the model results, it is found that time, location characteristics, ringer mode, and user activity are effective in predicting availability. In addition, it is investigated how knowledge workers’ engagement/challenge levels during work hours are related to their personality traits, social norms in office environments, and mobile application usage. The results show that personality traits and mobile application usage during work hours are significantly related to the engagement and challenge levels, however, social norms have a marginal effect on them. The results of the study present valuable implications for further studies and mobile application designs, which aim to understand the individual differences of employees in office environments.