Mapping Topic Evolution Across Poetic Traditions
This work addresses the challenge of understanding cross-cultural poetic evolution for literary scholars and computational linguists, but it is incremental as it applies an existing method to new data.
The study tackled the problem of comparing semantic topic evolution across poetic traditions in four languages by applying Latent Dirichlet Allocation to large poetry corpora, resulting in the identification of similarities and disparities in topic trends over time from 1600 to 1925 A.D., which helped pinpoint specific literary epochs.
Poetic traditions across languages evolved differently, but we find that certain semantic topics occur in several of them, albeit sometimes with temporal delay, or with diverging trajectories over time. We apply Latent Dirichlet Allocation (LDA) to poetry corpora of four languages, i.e. German (52k poems), English (85k poems), Russian (18k poems), and Czech (80k poems). We align and interpret salient topics, their trend over time (1600--1925 A.D.), showing similarities and disparities across poetic traditions with a few select topics, and use their trajectories over time to pinpoint specific literary epochs.