Investigating industry norms of cyber security: a critical content analysis of PwC’s annual reports

This project shows how to build an automated text‑mining and content‑analysis system that evaluates how cybersecurity norms change in corporate annual reports. It draws on critical content analysis of industry reports such as those from PwC. The system uses natural‑language‑processing (NLP) techniques to automatically extract, classify, and track strategic security themes, leadership models, and benchmark metrics across several years. Typical cybersecurity tools mainly detect technical threats. In contrast, this framework fills the governance gap by examining how companies communicate their security expectations and benchmarks to stakeholders. It applies tokenization, named‑entity recognition (NER), and sentiment analysis to parse the unstructured text in annual reports and maps the results to standard cybersecurity

frameworks like NIST and ISO 27001. By automatically spotting shifts in industry norms, the system helps researchers and security officers see how corporate security language lines up with the actual threat landscape. It provides a clear method for reading PDF‑based corporate disclosures, creating thematic visualizations, and spotting gaps between technical security developments and high‑level corporate strategies.

Message: Hi FE, I need help with “Investigating industry norms of cyber security: a critical content analysis of PwC's annual reports” in “Information Technology”