On the use of spreading activation methods in automatic information
SIGIR '88 Proceedings of the 11th annual international ACM SIGIR conference on Research and development in information retrieval
Texture Features for Browsing and Retrieval of Image Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using information scent to model user information needs and actions and the Web
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Unsupervised Segmentation of Color-Texture Regions in Images and Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Cognitive walkthrough for the web
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The use of web structure and content to identify subjectively interesting web usage patterns
ACM Transactions on Internet Technology (TOIT)
Term Weighting Approaches in Automatic Text Retrieval
Term Weighting Approaches in Automatic Text Retrieval
Proceedings of the 2009 ACM symposium on Applied Computing
Dynamic content-page identification for media-rich websites
Multimedia Tools and Applications
| Hi-index | 0.00 |
In this work we present an approach to capture the total semantics in multimedia-multimodal web pages. Our research improves upon the state-of-the-art with two key features: (1) capturing the semantics of text and image-based media for static and dynamic web content; and (2) recognizing that information goals are defined by emergent user behavior and not statically declared by web design alone. Given a user session, the proposed method accurately predicts user information goals and presents them as a list of most relevant words and images. Conversely, given a set of information goals, the technique predicts possible user navigation patterns as network flow with a semantically-derived flow distribution. In the latter case, differences between predicted optimal and observed user navigation patterns highlight points of suboptimal website design. We compare this approach to other content-based techniques for modeling web-usage and demonstrate its effectiveness.