Museum: Multidimensional web page segment evaluation model
This addresses web information retrieval by providing a fine-grained evaluation approach, though it appears incremental as it builds on existing segment-level methods.
The paper tackles the problem of evaluating web page relevancy to a query by proposing a bottom-up model that assesses segments using six dimensions, enabling tasks like personalization and re-ranking.
The evaluation of a web page with respect to a query is a vital task in the web information retrieval domain. This paper proposes the evaluation of a web page as a bottom-up process from the segment level to the page level. A model for evaluating the relevancy is proposed incorporating six different dimensions. An algorithm for evaluating the segments of a web page, using the above mentioned six dimensions is proposed. The benefits of fine-granining the evaluation process to the segment level instead of the page level are explored. The proposed model can be incorporated for various tasks like web page personalization, result re-ranking, mobile device page rendering etc.