Abstract
I introduce semantic novelty--cosine distance between each paragraph's sentence embedding and the running centroid of all preceding paragraphs--as an information-theoretic measure of narrative structure at corpus scale. Applying it to 28,606 books in PG19 (pre-1920 English literature), I compute paragraph-level novelty curves using 768-dimensional SBERT embeddings, then reduce each to a 16-segment Piecewise Aggregate Approximation (PAA). Ward-linkage clustering on PAA vectors reveals eight canonical narrative shape archetypes, from Steep Descent (rapid convergence) to Steep Ascent (escalating unpredictability). Volume--variance of the novelty trajectory--is the strongest length-independent predictor of readership (partial rho = 0.32), followed by speed (rho = 0.19) and Terminal/Initial ratio (rho = 0.19). Circuitousness shows strong raw correlation (rho = 0.41) but is 93 percent correlated with length; after control, partial rho drops to 0.11--demonstrating that naive correlations in corpus studies can be dominated by length confounds. Genre strongly constrains narrative shape (chi squared = 2121.6, p < 10 to the power negative 242), with fiction maintaining plateau profiles while nonfiction front-loads information. Historical analysis shows books became progressively more predictable between 1840 and 1910 (T/I ratio trend r = negative 0.74, p = 0.037). SAX analysis reveals 85 percent signature uniqueness, suggesting each book traces a nearly unique path through semantic space. These findings demonstrate that information-density dynamics, distinct from sentiment or topic, constitute a fundamental dimension of narrative structure with measurable consequences for reader engagement. Dataset: this https URL
Abstract (translated)
我引入了一种语义新颖性度量——即每个段落句子嵌入与所有前序段落运行中心点之间的余弦距离,作为一种信息论视角下叙述结构的量化方法。该方法应用于PG19(1920年前英文文学)中的28,606本书籍,使用768维SBERT嵌入计算段落级新颖性曲线,然后将其缩减为包含16个区间的分段聚合近似(PAA)。基于Ward-linkage聚类方法对PAA向量进行分析后,揭示了八个典型的叙述形状原型,从“陡峭下降”(快速收敛)到“陡峭上升”(不断升级的不可预测性)。在体积——新颖性轨迹的方差方面,是除长度以外最强的读者吸引力预测指标(部分rho = 0.32),其次是速度(rho = 0.19)和终始比值(rho = 0.19)。曲折度显示了较强的原始相关性(rho = 0.41),但与长度的相关度达到93%;在控制长度影响后,部分rho下降至0.11——这证明了语料库研究中由于长度造成的混杂效应可以主导简单的关联分析。体裁强烈限制着叙述形状(卡方=2121.6, p < 10^-242),小说倾向于保持平坦的结构模式,而非虚构作品则更加前置信息加载。历史分析表明,在1840年到1910年间书籍变得日益可预测(T/I比率趋势r = -0.74, p = 0.037)。SAX分析显示有85%的独特标识性,意味着每本书都描绘了一条几乎独一无二的语义空间路径。这些发现证明了信息密度动态变化——区别于情感或主题内容——构成了叙述结构中的一个基本维度,并对读者参与度产生可测量的影响。 数据集:见此链接 [this https URL]
URL
https://arxiv.org/abs/2602.20647