Information Retrieval

CSC

84080

Information Retrieval

Information Retrieval (IR) is the process of extracting relevant documents or their parts from larger quantities of documents based on a query presented by the user. Data Mining (DM) is the process of analyzing large volumes of data using pattern recognition or knowledge discovery techniques to find meaningful information that is hidden within available data (such as trends and implicit relationships). Traditional IR and DM focus more on structured data stored in databases. However, databases are not the only means for the storage of information. The World Wide Web (WWW), as a global distributed information repository, has become the largest data sources in today’s world. With the great impact of the WWW, Web information processing has become one of the hottest research topics in both academic and industry. The major differences in between normal databases and the WWW is that Web information are semi-structured, which makes IR and DM more difficult. However, the Web also provides some useful information such as hyperlinks, presentation structures, and user visiting patterns, which are unavailable from normal databases. All these make Web IR and DM quite different from traditional IR and DM. Consisting of five parts, this course mainly discusses technologies of IR and DM on Web information. The first part is about Web information storage and presentation schemes. The second and third parts discuss basic IR and DM technologies. The fourth and fifth parts discuss how to make use of the semi-structured/heterogeneous data, hyperlinks information, and user visiting patterns on the World Wide Web for Web IR and DM. In addition, this course will also cover the topic of Web Information Extraction.

Offer as needed

Graduate School Graduate

No