TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes

TL;DR

TriTopic introduces a tri-modal graph-based framework for topic modeling that enhances stability, lexical precision, and multi-perspective analysis, outperforming existing methods across multiple datasets.

Contribution

It presents a novel tri-modal graph approach with iterative refinement and archetype-based representations, addressing key limitations of prior topic modeling techniques.

Findings

Achieves highest NMI scores across all tested datasets

Ensures 100% corpus coverage with no outliers

Outperforms existing methods like BERTopic, NMF, and LDA

Abstract

Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data perspective. We present TriTopic, a framework that addresses these weaknesses through a tri-modal graph fusing semantic embeddings, TF-IDF, and metadata. Three core innovations drive its performance: hybrid graph construction via Mutual kNN and Shared Nearest Neighbors to eliminate noise and combat the curse of dimensionality; Consensus Leiden Clustering for reproducible, stable partitions; and Iterative Refinement that sharpens embeddings through dynamic centroid-pulling. TriTopic also replaces the "average document" concept with archetype-based topic representations defined by boundary cases rather than centers alone. In benchmarks across 20 Newsgroups, BBC News, AG News, and Arxiv, TriTopic achieves the highest NMI on every dataset (mean NMI 0.575 vs. 0.513 for BERTopic, 0.416 for NMF, 0.299 for LDA), guarantees 100% corpus coverage with 0% outliers, and is available as an open-source PyPI library.