Textual Analysis of Sustainability Reports: Topics, Firm Value, and the Moderating Role of Assurance

This study investigated how specific sustainability topics disclosed in standalone sustainability reports influence firm value and whether third-party assurance moderates this relationship. Drawing on signaling, agency, stakeholder, and legitimacy theories, we applied latent Dirichlet allocation (LDA) to extract latent topics from U.S. corporate sustainability reports. We analyzed their impact on Tobin’s Q using panel regressions and supplement our findings with discrete Bayesian networks (DBNs) and Shapley additive explanations (SHAP) to capture non-linear patterns. We identified six core topics: environmental impact, sustainable consumption, daily necessities, socio-economic impact, healthcare, and operations. The results revealed that topics of healthcare and daily necessities have immediate and sustained positive effects on firm value, while environmental and socio-economic impact topics demonstrate lagged effects, primarily two years after disclosure. The presence of assurance, however, produces mixed outcomes: it enhances credibility in some cases, but reduces firm value in others, especially when applied to environmental and socio-economic disclosures. This suggests a dual signaling effect of assurance, potentially increasing investor scrutiny when gaps in performance are highlighted. Our findings underscore the importance of topic selection, consistency in reporting, and strategic application of assurance in ESG communications to maintain stakeholder trust and market value.