PhD in using AI techniques to interrogate and interpret voluntary and mandatory (non) financial disclosures

We are offering a self-funded PhD position with the Brunel Business School, focusing on the evolving field of corporate communication and disclosure.

If you have any questions about the project or would like to arrange an informal discussion, please reach out to Kevin McMeeking at kevin.mcmeeking@brunel.ac.uk.

Project description

Are you passionate about technology and understanding the role of communication in the business world? If so, we invite you to apply for a unique opportunity to join our research team.

The "Disclosure” project is dedicated to providing critical insights into how the world of corporate communication is evolving across the themes of financial text processing, corporate report narrative disclosures, and corporate conference calls. Our project aims to further develop a groundbreaking theory for understanding the (ab)use, effectiveness and economic effects of mandatory, and voluntary disclosures by corporate management.

We welcome proposals that focus on the use of natural language processing (NLP) corpus linguistics theory and corpus linguistics methodology to extract, code and interpret information from companies’ qualitative disclosures on a large-sample basis. The gathered text will then be coded and a new set of quantitative metrics will be constructed from structured and unstructured datasets. The method involves applying NLP methods (e.g. tokens, types, word/phrase frequency counts, machine learning etc) and corpus linguistics (e.g. collocation, concordance, word sketch) This will help us understand whether and how corporate management’s interactions with their stakeholders impact the success or failure of the firm, plus many other outcomes (e.g. Loughran and Macdonald, 2016).

Associated areas to this line of research can consider the role of technology in appraising the determinants and economic consequences of narrative disclosures in corporate reports (e.g., annual report, remuneration report, social and environmental report etc). This methodology involves a large sample econometric analysis of the properties of corporate report narratives and corporate characteristics, corporate behaviour and economic effects.

This work builds on the theoretical framing set out by Cooke, McMeeking and Zeff (2024) that categorises disclosure from purely voluntary, informative, and innovative to mandatory with substantial adverse consequences for non-disclosers. NLP is a field of artificial intelligence that is centred on the relationship between computers/machines and (in our case the English) language. The objective is to use linguistics, IT and machine learning techniques to read, understand, interpret and construct human language in a meaningful manner. Drawing from prior literature, (e.g. Loughran and Macdonald, 2011), the well-established NLP techniques include text preprocessing (e.g. tokenisation, stop-word removal, stemming), text representation (e.g. bag of words, TF-IDF, embeddings), understanding and generating (e.g. sentiment analysis, question answering, speech recognition, text-to-speech).

In the last few years, the growth in NLP applications has been huge with the advancement of virtual assistants (e.g. Siri, Alexa), translation (e.g. Google Translate), social media monitoring (e.g. sentiment of tweets), text search engines (e.g. Google search), chatbots (e.g. online banking and e-commerce) and health informatics (e.g. extracting insights from patient records).

This project will be archival empiricism with the chance to work with the output of regulators, managers, analysts, shareholders, and government (and agencies). The techniques we will use can be adapted to other fields in subsequent (post-PhD) work, e.g. measuring a firm’s legitimacy using social media (e.g. Etter et al., 2018).

Who we're looking for

The successful candidate should fulfil the entrance requirements for a PhD in the Brunel Business School. A prior understanding (ideally at a degree level) of accounting and finance is important. GCSE (or equivalent) Mathematics and English skills are required.

Start date

All PhD students must commence their registration and PhD training before 30 September 2025.

Enquiries and applications

Please send the requested information and any enquiries directly to Nanki Rathour at nankikaur.aathour@brunel.ac.uk who will advise about making a formal application

Find more information about applying for a PhD at Brunel.

If you would like to apply for funded studentships please submit your application and indicate which scholarship you are applying for in the application form. Find details of the funded studentships.

References

Cooke, T.E., McMeeking, K.P. and Zeff, S.A. (2024), "Voluntary and mandatory reporting: a continuum of disclosure", Pacific Accounting Review, Vol. 36 No. 5, pp. 561-579.

Loughran, T., & McDonald, B. (2011). When is a liability, not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of Finance, 66(1), 35-65.

Loughran, T., & McDonald, B. (2016). Textual analysis in accounting and finance: A survey. Journal of Accounting Research, 54(4), 1187-1230.

Etter, M., Colleoni, E., Illia, L., Meggiorin, K., & D’Eugenio, A. (2018).

Measuring organizational legitimacy in social media: Assessing citizens’ judgments with sentiment analysis. Business & Society, 57(1), 60-97.

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.