Date of Award

Summer 2023

Degree Type

Open Access Dissertation

Degree Name

Information Systems and Technology, PhD


Center for Information Systems and Technology

Advisor/Supervisor/Committee Chair

Wallace Chipidza

Dissertation or Thesis Committee Member

Samir Chatterjee

Dissertation or Thesis Committee Member

Chinazunwa Uwaoma

Terms of Use & License Information

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Rights Information

© 2023 Eve H Thullen


Information Collection, Information Extraction, Information Overload, Information Process, Information Visualization, Knowledge Graph

Subject Categories

Management Information Systems


Continuously increasing text data such as news, articles, and scientific papers from the Internet have caused the information overload problem. Collecting valuable information as well as coding the information efficiently from enormous amounts of unstructured textual information becomes a big challenge in the information explosion age. Although many solutions and methods have been developed to reduce information overload, such as the deduction of duplicated information, the adoption of personal information management strategies, and so on, most of the existing methods only partially solve the problem. What’s more, many existing solutions are out of date and not compatible with the rapid development of new modern technology techniques. Thus, an effective and efficient approach with new modern IT (Information Technology) techniques that can collect valuable information and extract high-quality information has become urgent and critical for many researchers in the information overload age. Based on the principles of Design Science Theory, the paper presents a novel approach to tackle information overload issues. The proposed solution is an automated information process model that employs advanced IT techniques such as web scraping, natural language processing, and knowledge graphs. The model can automatically process the full cycle of information flow, from information Search to information Collection, Information Extraction, and Information Visualization, making it a comprehensive and intelligent information process tool. The paper presents the model capability to gather critical information and convert unstructured text data into a structured data model with greater efficiency and effectiveness. In addition, the paper presents multiple use cases to validate the feasibility and practicality of the model. Furthermore, the paper also performed both quantitative and qualitative evaluation processes to assess its effectiveness. The results indicate that the proposed model significantly reduces the information overload and is valuable for both academic and real-world research.