Query construction for related document search based on user annotations

We often use various services for creating bookmarks, tags, highlights and other types of annotations while surfing the Web or just reading electronic documents. These annotations represent additional information on particular information source. We proposed a method for query construction to search for related documents to currently studied document. We use the document content where we concentrate on user created annotations as indicators of user's interest in particular parts of the document. Our method for query construction is based on spreading activation in a graph created from the document content. We evaluated proposed method within a service called Annota, which allows users to insert various types of annotations into web pages and PDF documents displayed in the web browser. We analyzed properties of various types of annotations inserted by users of Annota into documents. Based on these properties, we also performed a simulation to determine optimal parameters and compare proposed method against commonly used tf-idf based method.