Early detection of sustainability-related controversies permits reputational risk attribution to specific companies and the evaluation of subsequent material effects on prices. Controversy mapping is currently one of the most actively developing areas in financial natural language processing (NLP) analytics, network analysis, and sentiment analysis.  This session will comprise short presentations followed by a panel discussion aimed at addressing key data challenges in controversy mapping.  We will focus on real ‘big data’ sources, such as unstructured high-frequency text data derived from digital news and social media platforms, and their use to establish the links between controversies and share prices, understand the role of ‘market memory’ in market moves, and the material effects of controversy strength.