Utilizing Microblogs for Web Page Relevant Term Acquisition

摘要

To allow advanced processing of information available on the Web, the web content necessitates semantic descriptions (metadata) processable by machines. Manual creation of metadata even in a lightweight form such as (web page) relevant terms is for us humans demanding and almost an impossible task, especially when considering open information space such as the Web. New approaches are devised continuously to automate the process. In the age of the Social Web an important new source of data to mine emerges - social annotations of web content. In this paper we utilize microblogs in particular. We present a method for relevant domain terms extraction for web resources based on processing of the biggest microblogging service to date - Twitter. The method leverages social characteristics of the Twitter network to consider different relevancies of Twitter posts assigned to the web resources. We evaluated the method in a user experiment while observing its performance for different types of web content.