A legwork mechanism for improving the retrieval effectiveness of a search engine is proposed. The feedback of relevant/non-relevant information has been shown to be useful to effectively find most of the relevant web pages in the ranked search results. A suggesting module, a type of relevance feedback engine, can do this job fairly well, but does not perform as well when the feedback information is only about non-relevant webpages. In such an unfavorable circumstance the legwork mechanism assists the suggesting module by handing over the relevant information after finding one or more webpages, containing at least one clue keyword. With a slight increase in time required to select the clue(s) in a presented candidate list, a user is able to find relevant webpages more effectively. The effect of the legwork mechanism was evaluated using various search results on the Japanese search engine goo.

Image annotation becomes increasingly more important as the Web continues to grow. We propose a novel approach to enhancing keyword-based Web-image annotation in folksonomy, where a volunteer user is notified what kind(s) of keywords are necessary, and that keywords have been sufficiently provided by other volunteer users. Necessary information is obtained from the keyword-filled facet tables, and sufficient information provided by the quantified conceptual keyword relations. Though the facet tables and the conceptual keyword relations are set by referring to an ontology, users do not need to know its details to successfully annotate the images.

Abstract A model of browsing‐based conceptual information retrieval is proposed employing two different types of dictionaries, a global dictionary and a local dictionary. A global dictionary with the authorized terms is utilized to capture the commonly acknowledgeable conceptual relation between a query and a document by replacing their keywords with the dictionary terms. The documents are ranked by the conceptual closeness to a query, and are arranged in the form of a user's personal digital library, or pDL. In a pDL a user can browse the arranged documents based on a suggestion about which documents are worth examining. This suggestion is made by the information in a local dictionary that is organized so as to reflect a user's interest and the association of keywords with the documents. Experiments for testing the retrieval performance of utilizing the two types of dictionaries were also performed using standard test collections.

A method of assisting a user in finding the required documents effectively is proposed. A user being informed which documents are worth examining can browse in a digital library (DL) in a linear fashion. Computational evaluations were carried out, and a DL and its navigator are designed and constructed.