Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large language model for Bible sentiment analysis: Sermon on the Mount

Mahek Vora, Tom Blau, Vansh Kachhwal, Ashu M. G. Solo, Rohitash Chandra

TL;DR

This work addresses how sentiment and semantics differ across English translations of the Sermon on the Mount by applying a transformer-based sentiment framework. It leverages SBERT with Senwave for multi-label sentiment and AFINN for polarity across five translations (KJV, NIV, NRSV, LV, BEV), examining verse-level and chapter-level patterns alongside bi-gram/tri-gram vocabulary analyses. The findings show substantial translation-driven vocabulary variation, with recurring concepts like 'kingdom of heaven' and varying humor detections; Chapter 6 tends to be more optimistic while Chapter 7 can appear more pessimistic or joking, depending on the translation. The study demonstrates the potential of LLM-based sentiment analysis for comparative religious linguistics and translation quality assessment, and it provides a framework that can be extended to additional texts and languages.

Abstract

The revolution of natural language processing via large language models has motivated its use in multidisciplinary areas that include social sciences and humanities and more specifically, comparative religion. Sentiment analysis provides a mechanism to study the emotions expressed in text. Recently, sentiment analysis has been used to study and compare translations of the Bhagavad Gita, which is a fundamental and sacred Hindu text. In this study, we use sentiment analysis for studying selected chapters of the Bible. These chapters are known as the Sermon on the Mount. We utilize a pre-trained language model for sentiment analysis by reviewing five translations of the Sermon on the Mount, which include the King James version, the New International Version, the New Revised Standard Version, the Lamsa Version, and the Basic English Version. We provide a chapter-by-chapter and verse-by-verse comparison using sentiment and semantic analysis and review the major sentiments expressed. Our results highlight the varying sentiments across the chapters and verses. We found that the vocabulary of the respective translations is significantly different. We detected different levels of humour, optimism, and empathy in the respective chapters that were used by Jesus to deliver his message.

Large language model for Bible sentiment analysis: Sermon on the Mount

TL;DR

This work addresses how sentiment and semantics differ across English translations of the Sermon on the Mount by applying a transformer-based sentiment framework. It leverages SBERT with Senwave for multi-label sentiment and AFINN for polarity across five translations (KJV, NIV, NRSV, LV, BEV), examining verse-level and chapter-level patterns alongside bi-gram/tri-gram vocabulary analyses. The findings show substantial translation-driven vocabulary variation, with recurring concepts like 'kingdom of heaven' and varying humor detections; Chapter 6 tends to be more optimistic while Chapter 7 can appear more pessimistic or joking, depending on the translation. The study demonstrates the potential of LLM-based sentiment analysis for comparative religious linguistics and translation quality assessment, and it provides a framework that can be extended to additional texts and languages.

Abstract

The revolution of natural language processing via large language models has motivated its use in multidisciplinary areas that include social sciences and humanities and more specifically, comparative religion. Sentiment analysis provides a mechanism to study the emotions expressed in text. Recently, sentiment analysis has been used to study and compare translations of the Bhagavad Gita, which is a fundamental and sacred Hindu text. In this study, we use sentiment analysis for studying selected chapters of the Bible. These chapters are known as the Sermon on the Mount. We utilize a pre-trained language model for sentiment analysis by reviewing five translations of the Sermon on the Mount, which include the King James version, the New International Version, the New Revised Standard Version, the Lamsa Version, and the Basic English Version. We provide a chapter-by-chapter and verse-by-verse comparison using sentiment and semantic analysis and review the major sentiments expressed. Our results highlight the varying sentiments across the chapters and verses. We found that the vocabulary of the respective translations is significantly different. We detected different levels of humour, optimism, and empathy in the respective chapters that were used by Jesus to deliver his message.
Paper Structure (14 sections, 8 figures, 2 tables)

This paper contains 14 sections, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. The Bible
  4. Bible Translations
  5. NLP for religious texts
  6. Methodology
  7. Data: Bible - Sermon of Mount
  8. Large language models for sentiment analysis
  9. Framework
  10. Results
  11. Data analysis
  12. Sentiment Analysis
  13. Discussion
  14. Conclusions

Figures (8)

  • Figure 1: Framework diagram showing major components that include preprocessing and sentiment analysis across translations of Sermon on the Mount.
  • Figure 2: Visualisation of top 10 bi-grams and tri-grams for the selected versions of Sermon on the Mount.
  • Figure 3: Visualisation of top 10 bi-grams and tri-grams for the selected versions of Sermon on the Mount.
  • Figure 4: Cumulative sentiments of the respective chapters.
  • Figure 5: Polarity Of Jesus's Speech
  • ...and 3 more figures