A Turkish Topic Modeling Dataset For Multi-label Classification of Movie Genre

Abstract

Statistical topic modeling aims to assign topics to documents in an unsupervised way. Latent Dirichlet Allocation (LDA) is the standard model for topic modeling. It shows good performance on document collections, documents being relatively long texts but it has poor performance on short texts. Topic modeling on short texts is on the rise due to the potential of social media. Thus, approaches that are able to find topics on short texts as well as long texts are sought. However, there is a lack of datasets that include both long and short texts which have the same ground-truth categories. In this work, we release a Turkish movie dataset which contain both short film descriptions and long subscripts where film genre can be considered as topic. Furthermore, we provide multi-label movie genre classification results using a Feed Forward Neural Network (FFNN) taking LDA document-topic or Doc2Vec dense representations.