| dc.description.abstract | Understanding personal characteristics and patterns that impact productivity on a personal level and using this information to support individuals has been recognized as being essential in improving personal productivity. However, existing studies often lack a versatile, personalized approach. This research aims to contribute to this problem by exploring the impact of work-related factors on perceived productivity among university staff. The main goal of this research is designing a workflow support system that identifies personal work related factors and aids the user in being more productive whilst working. These work-related factors include time-related
features like day of the week and sequential patterns of work activities. A combination of neural networks, pattern mining and data analytics is used to investigate the impact of work-related factors on productivity. Data was collected from four university staff members over a total period of around six months, and consists of log data regarding work-related activity tracked by Active Window Tracking software. This data is combined with survey data consisting of daily perceived productivity scores to gain insights on work-related factors and their impact on productivity.
The results show the significant impact of time-related features, work activities, and sequential patterns of work activities on perceived productivity. Additionally, the individual differences in work-related features that impact perceived productivity are shown, supporting the need for a personalized solution. However, the results of designing and evaluating the personalized workflow support system show the challenges of designing such a personalized solution that will be adopted by the user.
This research addressed gaps in the existing literature by focusing on work-related factors that impact perceived productivity over an extended period of time and can serve as a foundation for future personalized solutions that support individuals in
being more productive. Additionally, it emphasises the need for future research in applying our approach in different contexts with a broader set of work-related factors, more participants and a more detailed measure of productivity. Finally, implementing and assessing the user experience of workflow support systems in realworld scenarios will be crucial for developing effective tools for improving personal productivity. | |
