Interdisciplinary researcher with 15 years of experience using machine-learning, natural language processing, and data-visualization to analyze large language corpora. I turn stories into data, and tell stories with data. My work combines deep domain knowledge with technical skills to translate qualitative language into scalable computational representations and communicate quantitative models and data in visually and rhetorically accessible and persuasive ways for non-specialist audiences. I have extensive experience with language embedding techniques, time-series, and network analysis with a focus on developing models for sentiment analysis, stylometrics, domain-specific vocabulary extraction, similarity metrics, clustering and classification.