A Topic Modeling and Sentiment Analysis Model for Detection and Visualization of Themes in Literary Texts

Abstract

Despite the growing emergence of new computer analytic software programs, the adoption and application of computer-based data mining and processing methods remain sparse in literary studies and analyses. This study proposes a text analytics lifecycle to detect and visualize the prevailing themes in a corpus of literary texts. Two objectives are to be pursued: First, the study seeks to apply a Topic Modeling approach with selected algorithms of LDA, LSI, NMF, and HDP that can effectively detect the recurring topics about the major themes developed in the dataset. Second, the project aims to apply a Sentiment Analysis model that can analyze the polarity of writers’ discourse on the detected thematic topics with the algorithms of Vader and TextBlob. The implementation of Topic Modeling has detected six thematic topics of sex, family, revolution, imprisonment, intellectual, and death. The adoption of the Sentiment Analysis model also revealed that the feelings attached to all the identified themes are largely negative sentiments expressed towards socio-political issues.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 39 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.