Document Type
Poster
Publication Date
Spring 2025
Abstract
This study conducts an exploratory data analysis (EDA) of topic modeling and sentiment analysis applied to the Septuagint (LXX – the Greek translations of the Old Testament and the New Testament in the original Koine Greek) as well as four English translations of the Bible (LSV, Darby, DR, and KJV). Utilizing Latent Dirichlet Allocation (LDA) for topic modeling, I compare the Vulgate-based translations to Septuagint-based translations, discovering marked differences between the two categories of translations. The Vulgate is the Latin translation of the Bible done by Jerome in 900 A. D. which is already one step away from the original Greek; another layer of separation into the English translation does prove to display a meaningful difference in delivery of content. Taking stand out words surrounding domesticity from the topics (such as bread, tent, servant, harvest), I put the original Greek words through Voyant Tools as well as a sentiment analysis notebook. In observing the data, I discovered that in the Gospels, Jesus uses domestic words in two senses: the physical and earthly, and the metaphysical and spiritual. When using the word, for example, servant in a physical sense, the sentiment is more negative; when using it in the sense of the servant of the Lord, these domestic words result in a more positive sentiment.
Recommended Citation
Enright, Anne-Duncan, "NLP Analysis of the Septuagint: Topic Modeling and Sentiment Analysis of Biblical Domestic Terms" (2025). IPHS 484: Senior Seminar. Paper 40.
https://digital.kenyon.edu/dh_iphs_ss/40
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.