IDENTIFICATION OF TECHNOLOGY-RELEVANT ENTITIES BASED ON TREND CURVES AND SEMANTIC SIMILARITIES

PageRank evaluates the importance of Web pages with link relations. However, there is no direct method of evaluating the meaning of links in a hyperlink-based Web structure. This feature may cause problems in that pages containing many in-links are highly ranked without considering the meaning of the link relations among the pages. We therefore propose a novel ranking approach to directly analyze the meaning of links by transforminga hyperlink-based Web structure into a semantic-link-based Web structure. We extract semantic metadata from Web pages and construct a semantic-link-based Web structure using RDF model. We define a metric to evaluate the weight of the links for stratifyingrank values based on their importance in the semantic-link-based Web structure. We implement the weighted semantic ranking algorithm in the MapReduce framework to consider large-scale semantic metadata. The results of our experiment show that our approachoutperforms existing PageRank algorithms