Examining the ability of big data analytics to investigate financial reporting quality: a comprehensive bibliometric analysis

Abstract

Purpose

This study aims to examine the ability of big data analytics (BDA) to investigate financial reporting quality (FRQ), identify the knowledge base and conceptual structure of this research field and explore BDA techniques used over time.

Design/methodology/approach

This study uses a comprehensive bibliometric analysis approach (performance analysis and science mapping) using software packages, including Biblioshiny and VOSviewer. Multiple analyses are conducted, including authors, sources, keywords, co-citations, thematic evolution and trend topic analysis.

Findings

This study reveals that the intellectual structure of using BDA in investigating FRQ encompasses three clusters. These clusters include applying data mining to detect financial reporting fraud (FRF), using machine learning (ML) to examine FRQ and detecting earnings management as a measure of FRQ. Additionally, the results demonstrate that ML and DM algorithms are the most effective techniques for investigating FRQ by providing various prediction and detection models of FRF and EM. Moreover, BDA offers text mining techniques to detect managerial fraud in narrative reports. The findings indicate that artificial intelligence, deep learning and ML are currently trending methods and are expected to continue in the coming years.

Originality/value

To the best of the authors’ knowledge, this study is the first to provide a comprehensive analysis of the current state of the use of BDA in investigating FRQ.