出版社：Université Catholique de Louvain, Katholieke Universiteit Leuven
摘要：Our project—the Graph Poem (#GraphPoem)—focuses on poetry as a genre with the purpose to automate the reading of asmany–if not, ideally, all–poetic features, and then quantify and deploy them in representing and analyzing poetic corpora asnetworks. The article argues for and illustrates the benefits–to both digital humanities (DH) and natural language processing(NLP)–of setting out to computationally analyze poetry comprehensively. While comprehensiveness can only beasymptotically pursued in such a complex genre, the specifics such pursuit involves (with its in-depth analysis of each particularpoetic feature) branch out at times into other genres and more multiple and diverse text analysis aspects. The poetic featureswe focus on here are rhyme and diction, and metaphor, and our system establishes a computational model that classifiespoems based on similarities. For rhyme analysis, we investigate the methods used to classify poems based on rhyme patternsand we achieve an accuracy of 96.51% in identifying rhymes in poetry by applying a phonetic similarity model. For dictionanalysis, we investigate the classification methods and also build a word embeddings model on our poetry dataset. The analysisof these classifiers occasions reflections on the complexity of computational poetry analysis and the prospects of our projectat the crossroads of NLP, machine learning more generally, graph theory applications, and DH, as well as at the confluenceof research and creative work.
