CobwebTM: Probabilistic Concept Formation for Lifelong and Hierarchical Topic Modeling

TL;DR

CobwebTM is an online hierarchical topic model that uses incremental probabilistic concept formation with document embeddings to discover and organize topics dynamically without predefining their number.

Contribution

It adapts the Cobweb algorithm to continuous embeddings, enabling lifelong, hierarchical, and unsupervised topic modeling with minimal tuning.

Findings

Achieves strong topic coherence across datasets

Maintains stable topics over time

Constructs high-quality semantic hierarchies

Abstract

Topic modeling seeks to uncover latent semantic structure in text corpora with minimal supervision. Neural approaches achieve strong performance but require extensive tuning and struggle with lifelong learning due to catastrophic forgetting and fixed capacity, while classical probabilistic models lack flexibility and adaptability to streaming data. We introduce CobwebTM, a low-parameter lifelong hierarchical topic model based on incremental probabilistic concept formation. By adapting the Cobweb algorithm to continuous document embeddings, CobwebTM constructs semantic hierarchies online, enabling unsupervised topic discovery, dynamic topic creation, and hierarchical organization without predefining the number of topics. Across diverse datasets, CobwebTM achieves strong topic coherence, stable topics over time, and high-quality hierarchies, demonstrating that incremental symbolic concept formation combined with pretrained representations is an efficient approach to topic modeling.