The Historical Significance of Textual Distances
This addresses the problem of validating textual similarity for cultural analysis, but it is incremental as it builds on existing methods with new data and strategies.
The paper investigates whether textual similarity measures correspond to cultural proximity by comparing textual and social measures of similarities between English-language fiction genres, finding that new supervised learning strategies anchor textual measurement in social context.
Measuring similarity is a basic task in information retrieval, and now often a building-block for more complex arguments about cultural change. But do measures of textual similarity and distance really correspond to evidence about cultural proximity and differentiation? To explore that question empirically, this paper compares textual and social measures of the similarities between genres of English-language fiction. Existing measures of textual similarity (cosine similarity on tf-idf vectors or topic vectors) are also compared to new strategies that use supervised learning to anchor textual measurement in a social context.