Cross-Device Dataset Collection
Description: Currently, many applications or websites have different designs (layouts) for desktop and mobile interfaces. They may further bring different usability and user experience, which can be implicitly measured by users' behaviour. However, existing cross-device datasets contain either only user interfaces [1] or user behaviour [2,3]. In this project, you will collect a novel cross-device dataset that records both UIs and interactive behaviour.
Goal:
- Implement a recording system on mobile (phone and tablet) and/or desktop devices (can use existing GitHub codebases)
- Recruit participants to collect data
- Analyse the collected data: Statistics, behaviour patterns, usability, etc.
Supervisor: Guanhua Zhang
Distribution: 10% Literature, 50% Recording system implementation, 20% Data collection, 20% Data analysis
Requirements: Strong Python/HTML/Javascript skills, knowledge about database
Preferred: Practical experience in web/mobile/App development
Literature:
[1] Hu et al., Pairwise GUI Dataset Construction Between Android Phones and Tablets, NeurIPS’23 Track on Datasets and Benchmarks </i>
[2] Belman et al., SU-AIS BB-MAS (Syracuse University and Assured Information Security - Behavioral Biometrics Multi-device and multi-Activity data from Same users) Dataset, IEEE Dataport, 2019</i>
[3] Yuan et al., Generating Virtual Reality Stroke Gesture Data from Out-of-Distribution Desktop Stroke Gesture Data, IEEE VR’24