Investigation of Turkish Literary Poetry by Unsupervised Text Mining Methods

Akgun A. N., Calisir Z. D., Kaya T.

International Conference on Intelligent and Fuzzy Systems, INFUS 2021, İstanbul, Turkey, 24 - 26 August 2021, vol.307, pp.901-909 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 307
  • Doi Number: 10.1007/978-3-030-85626-7_105
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.901-909
  • Keywords: Literature mining, Machine learning, Period of national literature, Poem analysis, Republic period literature, Sentiment analysis, Text mining analysis in the Turkish language
  • Istanbul Technical University Affiliated: Yes


© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.With this study, it is aimed to analyze the change in Turkish literature with unsupervised text mining techniques based on the poems in the National Literature Period and the Republic Period. The reason for the election of these two periods is that there were changes in the Turkish language between periods and the establishment of the republic created changes in the feelings and thoughts of the people. To do this analysis, a data set including 116 republican period poems and 93 national period poems was created. The prominent issues of the periods and the public opinion were interpreted as a result of the studies. Sentiment analysis was made on poems and the changes in feelings experienced by the nation were also examined. The poems are divided into both positives and overwhelming emotions. They are divided into “surprising”, “happy”, “sad”, “disgust”, “fear”, and “anger” categories to examine feelings in more detail. When the project outputs were examined, it was seen that after the declaration of the republic, the positivity in the poems increased and the feelings became more balanced.