All Title Author
Keywords Abstract


A Comparative Study to Understanding about Poetics Based on Natural Language Processing

DOI: 10.4236/ojml.2017.75017, PP. 229-237

Keywords: Poets, Natural Language Processing, Word Vector Model, Similarity, Cluster Analysis

Full-Text   Cite this paper   Add to My Lib

Abstract:

This paper tries to find out five poets’ (Thomas Hardy, Wilde, Browning, Yeats, and Tagore) differences and similarities through analyzing their works on nineteenth Century by using natural language understanding technology and word vector model. Firstly, we collect enough poems from these five poets, build five corpus respectively, and calculate their high-frequency words, by using Natural Language Processing method. Then, based on the word vector model, we calculate the word vectors of the five poets’ high-frequency words, and combine the word vectors of each poet into one vector. Finally, we analyze the similarity between the combined word vectors by using the hierarchical clustering method. The result shows that the poems of Hardy, Browning, and Wilde are similar; the poems of Tagore and Yeats are relatively close—but the gap between the two is relatively large. In addition, we evaluate the stability of our approach by altering the word vector dimension, and try to analyze the results of clustering in a literary (poetic) perspective. Yeats and Tagore possessed a kind of mysticism poetics thought, while Hardy, Browning, and Wilde have the elements of realism combined with tragedy and comedy. The results are similar comparing to those we get from the word vector model.

References

[1]  Attabi, Y., & Dumouchel, P. (2013). Anchor Models for Emotion Recognition from Speech. IEEE Transactions on Affective Computing, 4, 1-11.
https://doi.org/10.1109/T-AFFC.2013.17
[2]  Baike (2017). Natural Language Toolkit.
https://baike.baidu.com/item/NLTK/20403245?fr=aladdin
[3]  Blackcatpoems (2017). Robert Browning.
http://www.blackcatpoems.com/b/robert_browning.html
[4]  Bryant, L. J. (2016). The History of Deep Learning. CSDN Blog.
http://blog.csdn.net/u012177034/article/details/52252851
[5]  Imagination Tech (2017). The History and Problems of Deep Learning in Natural Language.
http://www.sohu.com/a/161325083_468740
[6]  Ma, L. (2009). On the Topics of Tradedy, Love & Marriage, and Christianity in Thomas Hardy’s Novels and Poetry. M. Thesis in Aesthetics, Tianjing Normal University, 8-11.
[7]  Maas, A. L., & Ng, A. Y. (2011). A Probabilistic Model for Semantic Word Vectors. 1-8.
[8]  Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. Computer Science, 1-12.
[9]  Niketim (2016). The Introduction of Word Vector. CSDN Blog.
http://blog.csdn.net/u013362975/article/details/53319002
[10]  Poemhunter (2017). Oscar Wilde Poems. https://www.poemhunter.com/oscar-wilde
[11]  Poemhunter (2017). Thomas Hardy Poems. https://www.poemhunter.com/thomas-hardy
[12]  Rhys (2017). Rosenblatt’s Perceptron Algorithm.
http://blog.sina.com.cn/s/blog_166b82f8b0102xcu3.html
[13]  Sreeja, P. S., & Mahalakshmi, G. S. (2016). Comparison of Probabilistic Corpus Based Method and Vector Space Model for Emotion Recognition from Poems. Asian Journal of Information Technology, 15, 908-915.
[14]  Sun, C. W. (2012). Literature Review of Research on Wilde’s Works in the Past Thirty Years (pp. 1-4). Shenyang: Liaoning University.
[15]  Tagore, R. (2011). Gitanjali. Annals of Neuroscience, 18, 66.
[16]  Wang, X. S. (2012). The Comparison of Tagore and Yeats’ Poetic Thoughts (pp. 1-3). M.Sc. Thesis, Chongqing: Chongqing Southwest University.
[17]  Yeats, W. B. (1951). The Collected Poems of W.B. Yeats. Wordsworth Poetry Library, 1, 118-134.
[18]  Yuhushangwei (2016). The Calculation Method and Application of Cosine Similarity.
http://blog.csdn.net/yuhushangwei/article/details/48541891
[19]  Zhang, W. (2007). On the Cinematic Narrative Feature of Robert Browning’s Poetry (pp. 5-7). M.Sc. Thesis, Hangzhou: Zhejiang University.
[20]  Zhou Y. Y., & Fan, L. (2016). Deep Learning on Improved Word Embedding Model for Topic Classification. Computer Science and Application, 6, 629-637.
https://doi.org/10.12677/CSA.2016.611077

Full-Text

comments powered by Disqus