Machine learning and expert judgement: analysing emerging topics in accounting and finance research in the Asia–Pacific

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this paper, we focus on the question to what extent machine learning (ML) tools can be used to support systematic literature reviews. We apply a ML approach for topic detection to analyze emerging topics in the literature—our context is accounting and finance research in the Asia–Pacific region. To evaluate the robustness of the approach, we compare findings from the automated ML approach with the results from a manual analysis of the literature. The automated approach uses a keyword algorithm detection mechanism whereby the manual analysis uses common techniques for qualitative data analysis, that is, triangulation between researchers (expert judgement). From our paper, we conclude that both methods have strengths and weaknesses. The automated analysis works well for large corpora of text and provides a very standardized and non‐biased way of analyzing the literature. However, the human researcher is potentially better equipped to evaluate current issues and future trends in the literature. Overall, the best results might be achieved when a variety of tools are used together.
LanguageEnglish
Pages709-733
Number of pages25
JournalAbacus-A Journal Of Accounting Finance And Business Stud
Volume55
Issue number4
Early online date21 Nov 2019
DOIs
Publication statusPublished - Dec 2019

Fingerprint

Asia-Pacific
Expert judgment
Finance
Machine learning
Triangulation
Asia-Pacific region
Literature review
Qualitative data
Robustness
Future trends
Key words

Keywords

  • Accounting research
  • Asia–Pacific
  • Entity Linking
  • Environmental finance
  • Finance research
  • Research agenda
  • Research trends
  • Review

Cite this

@article{3bfaf4fff1bf446cb28324e7531aa61a,
title = "Machine learning and expert judgement: analysing emerging topics in accounting and finance research in the Asia–Pacific",
abstract = "In this paper, we focus on the question to what extent machine learning (ML) tools can be used to support systematic literature reviews. We apply a ML approach for topic detection to analyze emerging topics in the literature—our context is accounting and finance research in the Asia–Pacific region. To evaluate the robustness of the approach, we compare findings from the automated ML approach with the results from a manual analysis of the literature. The automated approach uses a keyword algorithm detection mechanism whereby the manual analysis uses common techniques for qualitative data analysis, that is, triangulation between researchers (expert judgement). From our paper, we conclude that both methods have strengths and weaknesses. The automated analysis works well for large corpora of text and provides a very standardized and non‐biased way of analyzing the literature. However, the human researcher is potentially better equipped to evaluate current issues and future trends in the literature. Overall, the best results might be achieved when a variety of tools are used together.",
keywords = "Accounting research, Asia–Pacific, Entity Linking, Environmental finance, Finance research, Research agenda, Research trends, Review",
author = "Cynthia Cai and Martina Linnenluecke and Mauricio Marrone and Singh, {Abhay K.}",
year = "2019",
month = "12",
doi = "10.1111/abac.12179",
language = "English",
volume = "55",
pages = "709--733",
journal = "Abacus: journal of accounting, finance and business studies",
issn = "0001-3072",
publisher = "Blackwell Publishing",
number = "4",

}

TY - JOUR

T1 - Machine learning and expert judgement

T2 - Abacus: journal of accounting, finance and business studies

AU - Cai, Cynthia

AU - Linnenluecke, Martina

AU - Marrone, Mauricio

AU - Singh, Abhay K.

PY - 2019/12

Y1 - 2019/12

N2 - In this paper, we focus on the question to what extent machine learning (ML) tools can be used to support systematic literature reviews. We apply a ML approach for topic detection to analyze emerging topics in the literature—our context is accounting and finance research in the Asia–Pacific region. To evaluate the robustness of the approach, we compare findings from the automated ML approach with the results from a manual analysis of the literature. The automated approach uses a keyword algorithm detection mechanism whereby the manual analysis uses common techniques for qualitative data analysis, that is, triangulation between researchers (expert judgement). From our paper, we conclude that both methods have strengths and weaknesses. The automated analysis works well for large corpora of text and provides a very standardized and non‐biased way of analyzing the literature. However, the human researcher is potentially better equipped to evaluate current issues and future trends in the literature. Overall, the best results might be achieved when a variety of tools are used together.

AB - In this paper, we focus on the question to what extent machine learning (ML) tools can be used to support systematic literature reviews. We apply a ML approach for topic detection to analyze emerging topics in the literature—our context is accounting and finance research in the Asia–Pacific region. To evaluate the robustness of the approach, we compare findings from the automated ML approach with the results from a manual analysis of the literature. The automated approach uses a keyword algorithm detection mechanism whereby the manual analysis uses common techniques for qualitative data analysis, that is, triangulation between researchers (expert judgement). From our paper, we conclude that both methods have strengths and weaknesses. The automated analysis works well for large corpora of text and provides a very standardized and non‐biased way of analyzing the literature. However, the human researcher is potentially better equipped to evaluate current issues and future trends in the literature. Overall, the best results might be achieved when a variety of tools are used together.

KW - Accounting research

KW - Asia–Pacific

KW - Entity Linking

KW - Environmental finance

KW - Finance research

KW - Research agenda

KW - Research trends

KW - Review

UR - http://www.scopus.com/inward/record.url?scp=85075462149&partnerID=8YFLogxK

U2 - 10.1111/abac.12179

DO - 10.1111/abac.12179

M3 - Article

VL - 55

SP - 709

EP - 733

JO - Abacus: journal of accounting, finance and business studies

JF - Abacus: journal of accounting, finance and business studies

SN - 0001-3072

IS - 4

ER -