Author

Deepthi Katta

Award Date

5-2009

Degree Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science

First Committee Member

Kazem Taghva, Chair

Second Committee Member

Ajoy K. Datta

Third Committee Member

Laxmi P. Gewali

Graduate Faculty Representative

Muthukumar Venkatesan

Number of Pages

66

Abstract

Information Retrieval is the science of searching for information or documents based on information need from a huge set of documents. It has been an active field of research since early 19th century and different models of retrieval came in to existence to cater the information need.

This thesis starts with understanding some of the basic information retrieval models, followed by implementation of one of the most popular statistical retrieval model known as Vector Space Model. This model ranks the documents in the collection based on the similarity measure calculated between the query and the respective document. The user specifies the "information need" which is more commonly known as a "query" using the visual interface provided. The given query is then processed and the results are displayed to the user in a ranked order.

We then focus on the Relevance feedback, a technique that modifies the user query based on the characteristics of the document collection to improve the results. In this thesis, we explore different types and models of relevance feedback that can be applied to Vector Space model and how they affect the performance of the model.

Keywords

Information retrieval; Internet searching; Keyword searching; Vector spaces--Data processing

Disciplines

Computer Sciences | Databases and Information Systems | Theory and Algorithms

Language

English

Comments

Signatures have been redacted for privacy and security measures.


Share

COinS