Mobile devices are increasingly being used to access Web content but lack the resources for proper presentation to the user. To address this problem, content is typically customized to be more suitable for a mobile environment. Automatic customization of web content is a challenging problem because fine-grain adaptation often depends on both the relevance of individual objects on a web page, as well as the context of access (e.g., screen size of device being used, network connectivity, location, etc.). We present Usage-aware Interactive Content Adaptation, an adaptation technique that allows a user who is unsatisfied with the system’s adaptation decision to take control of the adaptation process and make changes until the content is suitably adapted for her purposes. The adaptation system learns from the user’s modifications and adjusts its prediction for future accesses by other users. With this approach, users are empowered to correct bad adaptation decisions made by the system without being overly burdened. We applied the technique in two domains: adapting the quality of images to reduce download times and save energy and bandwidth, and customizing the layout of images to improve the utilization of screen real-estate. The work was evaluated through a series of user studies, and the results show that user feedback can be effectively used to provide appropriate customizations (i) for objects with varying relevance, (ii) when context affects the users adaptation requirements, and (iii) when the same content can be used for multiple purposes by different users.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:OTU.1807/16739 |
| Date | 19 January 2009 |
| Creators | Mohomed, Iqbal |
| Contributors | de Lara, Eyal |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | en_ca |
| Detected Language | English |
| Type | Thesis |
| Format | 1050622 bytes, application/pdf |
Page generated in 0.0024 seconds