Degree
Doctor of Philosophy
Program
Computer Science
Supervisor
Dr. Roberto Solis-Oba
Abstract
Since its emergence, the Internet has changed the way in which information is distributed and it has strongly influenced how people communicate. Nowadays, Web search engines are widely used to locate information on the Web, and online social networks have become pervasive platforms of communication.
Retrieving relevant Web pages in response to a query is not an easy task for Web search engines due to the enormous corpus of data that the Web stores and the inherent ambiguity of search queries. We present two approaches to improve the effectiveness of Web search engines. The first approach allows us to retrieve more Web pages relevant to a user's query by extending the query to include synonyms and other variations. The second, gives us the ability to retrieve Web pages that more precisely reflect the user's intentions by filtering out those pages which are not related to the user-specified interests.
Discovering communities in online social networks (OSNs) has attracted much attention in recent years. We introduce the concept of subject-driven communities and propose to discover such communities by modeling a community using a posting/commenting interaction graph which is relevant to a given subject of interest, and then applying link analysis on the interaction graph to locate the core members of a community.
Recommended Citation
Mei, Guo, "Improving Search Engine Results by Query Extension and Categorization" (2011). Electronic Thesis and Dissertation Repository. 275.
https://ir.lib.uwo.ca/etd/275