Written communications about personal experiences, such as giving birth or reading a book, can be both rhetorically powerful and statistically difficult to model. My research explores unsupervised natural language processing (NLP) models to represent complex personal experiences and self-disclosures communicated in online communities, while also re-examining these models for biases and instabilities. I seek to reliably represent individual experiences within their social contexts and model interpretive dimensions that illuminate both patterns and outliers, while addressing social and humanistic questions. Through this work, I develop a data science practice that emphasizes cross-disciplinary collaborations and care for datasets and their authors. In this dissertation, I share case studies that highlight both the opportunities and the risks in reusing NLP models for context-specific research questions.