This chapter delineates big data and machine learning (ML) methods in innovation research. Large-scale data and computational methods are currently being used to advance innovation research on sources and processes. The chapter covers three oft-used computational methods: topic modeling for identifying latent themes, word embeddings for assessing semantic linkages, and generative large language models for text annotation and coding. Combined with large-scale data sets, these methods allow for nuanced and systematic analysis of innovation processes. The chapter also addresses the limitations of employing big data and ML methods in empirical studies, such as data quality and ethical considerations. It emphasizes the importance of human expertise and the potential of ML to aid as research assistants and interlocutors in social science innovation research.