Blurb-Refined Inference from Crowdsourced Book Reviews using Hierarchical Genre Mining with Dual-Path Graph Convolutions

TL;DR

This paper introduces HiGeMine, a hierarchical genre classification framework that combines review filtering and dual-path graph convolutional networks to improve accuracy in book genre prediction.

Contribution

The paper presents a novel two-phase approach integrating semantic review filtering with a dual-path graph-based classifier for hierarchical genre prediction.

Findings

HiGeMine outperforms baseline models on a new hierarchical genre dataset.

Semantic filtering reduces noise and improves classification accuracy.

Explicit modeling of genre dependencies enhances prediction performance.

Abstract

Accurate book genre classification is fundamental to digital library organization, content discovery, and personalized recommendation. Existing approaches typically model genre prediction as a flat, single-label task, ignoring hierarchical genre structure and relying heavily on noisy, subjective user reviews, which often degrade classification reliability. We propose HiGeMine, a two-phase hierarchical genre mining framework that robustly integrates user reviews with authoritative book blurbs. In the first phase, HiGeMine employs a zero-shot semantic alignment strategy to filter reviews, retaining only those semantically consistent with the corresponding blurb, thereby mitigating noise, bias, and irrelevance. In the second phase, we introduce a dual-path, two-level graph-based classification architecture: a coarse-grained Level-1 binary classifier distinguishes fiction from non-fiction, followed by Level-2 multi-label classifiers for fine-grained genre prediction. Inter-genre dependencies are explicitly modeled using a label co-occurrence graph, while contextual representations are derived from pretrained language models applied to the filtered textual content. To facilitate systematic evaluation, we curate a new hierarchical book genre dataset. Extensive experiments demonstrate that HiGeMine consistently outperformed strong baselines across hierarchical genre classification tasks. The proposed framework offers a principled and effective solution for leveraging both structured and unstructured textual data in hierarchical book genre analysis.