Persistent Homology of Topic Networks for the Prediction of Reader Curiosity

TL;DR

This paper introduces a novel method combining persistent homology and topic modeling to analyze semantic information gaps in texts, effectively predicting reader curiosity levels and advancing understanding of engagement in NLP.

Contribution

It presents a new framework that models reader curiosity through topological analysis of semantic networks, integrating persistent homology with topic modeling for the first time.

Findings

Topological features significantly improve curiosity prediction accuracy.

The pipeline explains 73% of variance in curiosity ratings.

Semantic network topology correlates with reader engagement.

Abstract

Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein's Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text's semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants (n = 49) as they read S. Collins's ''The Hunger Games'' novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73% vs. 30% explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement.