Date of Award

2020

Degree Type

Restricted to Claremont Colleges Dissertation

Degree Name

Information Systems and Technology, PhD

Program

Center for Information Systems and Technology

Advisor/Supervisor/Committee Chair

Brian Hilton

Dissertation or Thesis Committee Member

Anthony Corso

Dissertation or Thesis Committee Member

Lorne Olfman

Terms of Use & License Information

Terms of Use for work posted in Scholarship@Claremont.

Rights Information

© 2020 Sarah Y Osailan

Keywords

Decision Support Systems, Information Systems & Technology, Natural Language Processing, Social Media Analysis, Text Mining, Topic Modeling

Abstract

Topic modeling is a technique used in text analysis and mining across various research domains. The number of social media applications and users is increasing daily, and analyzing these data streams provides added value, relevance, and significance for both scholarly and practitioner communities. With increased users, the user-generated content grows, as do the value and information that are extracted from this data stream. The merging of analysis techniques for social media and text enables effective decision making in businesses, because it provides a communication-driven decision support system. This study focuses on combining machine learning and natural language processing techniques to investigate how time affects topics, as derived from tweets. It also examines the impact of observation and information on the decision-making process. The primary objectives of this dissertation were to develop an instantiation and to visualizes topics as derived from user-generated content on Twitter. The study also presents the results of a systematic literature review, which followed a hybrid methodology to illustrate various topic-modeling algorithms. The use of design science research methodology and CRISP-DM methodologies resulted in an instantiation artifact being developed. This served to visualize topic-modeling results using corpus periodization to observe topic-change detection as extracted from Twitter data feeds.

ISBN

9798641213309

Download

Share

COinS