Macquarie University
01whole.pdf (1.24 MB)

Read like a human: the role of quantified knowledge in market predictions

Download (1.24 MB)
posted on 2022-04-08, 05:49 authored by Tiancheng Wang

In this study, I propose a novel entity-specific sentiment index to examine how massive general knowledge can be quantified and used to extract better financial inferences from media outlets following a similar reasoning process as human news readers. With the advent of graph representation techniques, external knowledge can be represented by knowledge graphs, and then quantified through graph embedding processes. By modifying traditional sentiment analysis using quantified knowledge, I find that the introduction of external knowledge significantly and consistently improves the predictive power of sentiment indexes as indicators of stock market activity.


Table of Contents

Chapter 1: Introduction -- Chapter 2: Literature Review -- Chapter 3: Data Source -- Chapter 4: Methodology -- Chapter 5: In-Sample Regression Tests -- Chapter 6: Out-of-Sample Regression Tests -- Chapter 7: Conclusion – References -- Appendix


A thesis presented for the degree of Master of Research. Theoretical thesis. 18 May 2020. Includes bibliographical references (pages 60-63).

Awarding Institution

Macquarie University

Degree Type

Thesis MRes


Thesis MRes, Macquarie University, Macquarie Business School, 2020

Department, Centre or School

Department of Applied Finance

Year of Award


Principal Supervisor

Jing Shi

Additional Supervisor 1

Terry Pan


Copyright disclaimer: Copyright Tiancheng Wang 2020.




1 online resource (66 pages)