Date Approved

7-12-2018

Embargo Period

7-13-2018

Document Type

Thesis

Degree Name

MS Computer Science

Department

Computer Science

College

College of Science & Mathematics

First Advisor

Ho, Shen-Shyang

Second Advisor

Breitzman, Anthony

Third Advisor

Sun, Bo

Subject(s)

Electronic information resource searching; Semantic networks (Information theory)

Disciplines

Computer Sciences

Abstract

Information seekers are posed with multiple challenges in gathering an unbiased and comprehensive body of information. The costs of analyzing documents often drive searches toward a small subset of documents. Additionally, modern search tools may reinforce the confirmation bias of users by providing only those documents that closely match their search query. The end result is a decision or hypothesis that is ill-considered and substantiated by potentially biased information. Information seekers need an information foraging tool that can help them explore the document corpus to find relevant topics and text snippets, while finding the hidden information that may be buried in the corpus or may not have been known a priori.

An automated information foraging tool can mitigate these challenges by automatically identifying a wide breadth of topics for the user, extracted directly from a document corpus. When documents are decomposed and reconstituted into a semantic network, there is value in the topological structures formed. Leveraging a suite of information retrieval and graph analysis algorithms that analyze the semantic network, a framework is defined for assisting information seekers in both exploring and exploiting relevant information from a corpus to support unbiased decision making.

Share

COinS