# Stability of Topic Modeling via Matrix Factorization

arXiv: https://arxiv.org/abs/1702.07186 · HTML: https://mlsanity.com/paper/1702.07186/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2017.

## Built on by (most cited first, 13 of 13)

- [LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing](https://mlsanity.com/paper/2404.18001/) (2024)
- [Citizen Participation and Machine Learning for a Better Democracy](https://mlsanity.com/paper/2103.00508/) (2021)
- [A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data](https://mlsanity.com/paper/2106.06738/) (2021)
- [Determination of the Number of Topics Intrinsically: Is It Possible?](https://mlsanity.com/paper/2406.10402/) (2024)
- [Research Topic Flows in Co-Authorship Networks](https://mlsanity.com/paper/2206.07980/) (2022)
- [Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Media](https://mlsanity.com/paper/2410.12791/) (2024)
- [Evaluation of Non-Negative Matrix Factorization and n-stage Latent Dirichlet Allocation for Emotion Analysis in Turkish Tweets](https://mlsanity.com/paper/2110.00418/) (2021)
- [Supporting peace negotiations in the Yemen war through machine learning](https://mlsanity.com/paper/2207.11528/) (2022)
- [Machine Learning for Mediation in Armed Conflicts](https://mlsanity.com/paper/2108.11942/) (2021)
- [Mapping Research Trajectories](https://mlsanity.com/paper/2204.11859/) (2022)
- [Repeatability is not recovery: Quantifying algorithmic stability and topic recovery in Latent Dirichlet Allocation](https://mlsanity.com/paper/2511.12850/) (2025)
- [A Reproducible Framework for Neural Topic Modeling in Focus Group Analysis](https://mlsanity.com/paper/2511.18843/) (2025)
- [MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry](https://mlsanity.com/paper/2608.28315/) (2026)

## Abstract (arXiv)

Topic models can provide us with an insight into the underlying latent structure of a large corpus of documents. A range of methods have been proposed in the literature, including probabilistic topic models and techniques based on matrix factorization. However, in both cases, standard implementations rely on stochastic elements in their initialization phase, which can potentially lead to different results being generated on the same corpus when using the same parameter values. This corresponds to the concept of "instability" which has previously been studied in the context of k-means clustering. In many applications of topic modeling, this problem of instability is not considered and topic models are treated as being definitive, even though the results may change considerably if the initialization process is altered. In this paper we demonstrate the inherent instability of popular topic modeling approaches, using a number of new measures to assess stability. To address this issue in the context of matrix factorization for topic modeling, we propose the use of ensemble learning strategies. Based on experiments performed on annotated text corpora, we show that a K-Fold ensemble strategy, combining both ensembles and structured initialization, can significantly reduce instability, while simultaneously yielding more accurate topic models.