Designing content-driven intelligent notification mechanisms for mobile applications
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 24112578
- Type
- E - Conference contribution
- DOI
-
10.1145/2750858.2807544
- Title of conference / published proceedings
- UbiComp '15 Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing
- First page
- 813
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- September
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 48
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Intelligent, adaptive systems are important to reduce workload and improve interaction. It is demonstrated that the use of sensor data, message content and social relationships enables accurate prediction of notification acceptance. A real-world evaluation is used to collect user behavioural data and build individual models. This demonstrates that individual predictive models can be learned quickly and can outperform both user-defined rules and generic models. The work has led to PhD theses and positions in industrial research labs. There have been further extensions to areas such as inferring mental health. Other researchers have further developed these ideas.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -