Multidimensional Web Page Evaluation Model Using Segmentation And Annotations
This addresses a non-trivial problem in Information Retrieval for improving web page evaluation, but appears incremental as it builds on existing segmentation and annotation approaches.
The paper tackles the problem of context-sensitive, semantic evaluation of web pages by proposing a hybrid model that cumulates segment scores using structural and content semantics, with experiments confirming its efficiency.
The evaluation of web pages against a query is the pivot around which the Information Retrieval domain revolves around. The context sensitive, semantic evaluation of web pages is a non-trivial problem which needs to be addressed immediately. This research work proposes a model to evaluate the web pages by cumulating the segment scores which are computed by multidimensional evaluation methodology. The model proposed is hybrid since it utilizes both the structural semantics and content semantics in the evaluation process. The score of the web page is computed in a bottom-up process by evaluating individual segment's score through a multi-dimensional approach. The model incorporates an approach for segment level annotation. The proposed model is prototyped for evaluation; experiments conducted on the prototype confirm the model's efficiency in semantic evaluation of pages.