Language of Persuasion and Misrepresentation in Business Communication: A Textual Detection Approach

ArXiv ID: 2508.09935 “View on arXiv”

Authors: Sayem Hossen, Monalisa Moon Joti, Md. Golam Rashed

Abstract

Business communication digitisation has reorganised the process of persuasive discourse, which allows not only greater transparency but also advanced deception. This inquiry synthesises classical rhetoric and communication psychology with linguistic theory and empirical studies in the financial reporting, sustainability discourse, and digital marketing to explain how deceptive language can be systematically detected using persuasive lexicon. In controlled settings, detection accuracies of greater than 99% were achieved by using computational textual analysis as well as personalised transformer models. However, reproducing this performance in multilingual settings is also problematic and, to a large extent, this is because it is not easy to find sufficient data, and because few multilingual text-processing infrastructures are in place. This evidence shows that there has been an increasing gap between the theoretical representations of communication and those empirically approximated, and therefore, there is a need to have strong automatic text-identification systems where AI-based discourse is becoming more realistic in communicating with humans.

Keywords: Deceptive language detection, Transformer models, Computational textual analysis, Sustainable finance, Financial reporting, Equity/General Financial Reporting

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 4.0/10
• Quadrant: Philosophers
• Why: The paper applies computational linguistics and transformer models to detect deceptive language but lacks the mathematical formalism or heavy derivations typical of high-complexity work. While it reports high accuracies, the discussion of data limitations and lack of implementation details place it in a lower empirical rigor bracket, focusing more on theoretical synthesis than backtest-ready methodology.

  flowchart TD
    A["Research Goal:<br>How to detect deceptive language in<br>digitised business communication?"] --> B["Methodology: Synthesise & Model"]
    B --> C["Data Sources:<br>Financial Reporting<br>Sustainability Discourse<br>Digital Marketing"]
    C --> D["Computation:<br>Transformer Models &<br>Textual Analysis"]
    D --> E{"Evaluation"}
    E -- Controlled Settings --> F[">99% Accuracy"]
    E -- Multilingual Settings --> G["Data Scarcity &<br>Infrastructure Limits"]
    F & G --> H["Outcome: Theoretical-Practical<br>Gap; Need for Robust AI Systems"]