UMBC ebiquity
Presentation
Wikitology: Wikipedia as an ontology
January 9, 2008
1424295 bytes
PDF Document - Need a reader? Get one here
Identifying topics and concepts associated with a set of documents is a task common to many applications. It can help with the annotation and categorization of documents and be used to model a person's current interests to improve search results, support business intelligence, or select appropriate advertisements. One approach is to associate a document with a set of topics selected from a fixed ontology or vocabulary of terms. We have investigated using Wikipedia's articles and associated pages as a topic ontology for this purpose. The benefits of this approach are that the ontology terms are developed through a social process, maintained and kept current by the Wikipedia community, represent a consensus view, and have meaning that can be understood simply by reading the associated Wikipedia page. We use Wikipedia articles and the category and article link graphs to predict concepts common to a set of documents. We describe several algorithms we implemented and evaluated to aggregate and refine results, including spreading activation to select the most appropriate terms. While the Wikipedia category graph can be used to predict general concepts, the article links graph helps predict more specific concepts and concepts not in the category hierarchy. Our experiments show that it is possible to suggest new category concepts by identifying them as unions of pages from the page link graph. Such predicted concepts can be used to define new categories or sub-categories within Wikipedia.
2353 downloads
Public