Computational Analysis of Semantic Connections Between Herman Melville Reading and Writing

TL;DR

This paper employs computational semantic similarity analysis using BERTScore to explore Herman Melville's reading influences on his writings, demonstrating the method's effectiveness in identifying potential literary influences.

Contribution

It introduces a novel computational framework for analyzing literary influence through semantic similarity, combining document segmentation and BERTScore without fixed thresholds.

Findings

Successfully captures expert-identified similarities

Highlights additional passages for further study

Supports computational approaches in literary influence research

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.