Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Computational Analysis of Semantic Connections Between Herman Melville Reading and Writing

Nudrat Habib, Elisa Barney Smith, Steven Olsen Smith

Abstract

This study investigates the potential influence of Herman Melville reading on his own writings through computational semantic similarity analysis. Using documented records of books known to have been owned or read by Melville, we compare selected passages from his works with texts from his library. The methodology involves segmenting texts at both sentence level and non-overlapping 5-gram level, followed by similarity computation using BERTScore. Rather than applying fixed thresholds to determine reuse, we interpret precision, recall, and F1 scores as indicators of possible semantic alignment that may suggest literary influence. Experimental results demonstrate that the approach successfully captures expert-identified instances of similarity and highlights additional passages warranting further qualitative examination. The findings suggest that semantic similarity methods provide a useful computational framework for supporting source and influence studies in literary scholarship.

Computational Analysis of Semantic Connections Between Herman Melville Reading and Writing

Abstract

This study investigates the potential influence of Herman Melville reading on his own writings through computational semantic similarity analysis. Using documented records of books known to have been owned or read by Melville, we compare selected passages from his works with texts from his library. The methodology involves segmenting texts at both sentence level and non-overlapping 5-gram level, followed by similarity computation using BERTScore. Rather than applying fixed thresholds to determine reuse, we interpret precision, recall, and F1 scores as indicators of possible semantic alignment that may suggest literary influence. Experimental results demonstrate that the approach successfully captures expert-identified instances of similarity and highlights additional passages warranting further qualitative examination. The findings suggest that semantic similarity methods provide a useful computational framework for supporting source and influence studies in literary scholarship.
Paper Structure (9 sections, 4 figures, 2 tables, 1 algorithm)

This paper contains 9 sections, 4 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Semantic Similarity Results: Evidence of Possible Influence
  5. Expert Identified Instances: Validation of Semantic Similarity
  6. Model-Discovered Parallels: Additional Evidence of Influence
  7. Evaluating Similarity at Different Levels of Text Granularity
  8. Limitations and Future Work
  9. Conclusion

Figures (4)

  • Figure 1: 5-gram analysis: F1 scores for instance 1 in Table \ref{['instances']} comparing Typee with A visit to the south seas.
  • Figure 2: Sentence level analysis: F1 scores for instance 1 in Table \ref{['instances']} comparing Typee with A visit to the south seas.
  • Figure 3: Precision, recall and F1 score values for instance 4 from Table \ref{['instances']} comparing The Natural History of the Sperm Whale and Moby Dick
  • Figure 4: Heat map for complete text comparison of instance 2 in Table \ref{['instances']} comparing Life and Remarkable Adventures of Israel R. Potter with Israel Potter; His fifty years of exile at the sentence level.