# A network approach to topic models

arXiv: https://arxiv.org/abs/1708.01677 · HTML: https://mlsanity.com/paper/1708.01677/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2017.

## Built on by (most cited first, 25 of 25)

- [Generative hypergraph clustering: from blockmodels to modularity](https://mlsanity.com/paper/2101.09611/) (2021)
- [Scholastic: Graphical Human-Al Collaboration for Inductive and Interpretive Text Analysis](https://mlsanity.com/paper/2208.06133/) (2022)
- [Computational thematics: Comparing algorithms for clustering the genres of literary fiction](https://mlsanity.com/paper/2305.11251/) (2023)
- [Multilayer Networks for Text Analysis with Multiple Data Types](https://mlsanity.com/paper/2106.15821/) (2021)
- [Determination of the Number of Topics Intrinsically: Is It Possible?](https://mlsanity.com/paper/2406.10402/) (2024)
- [Analysis and tuning of hierarchical topic models based on Renyi entropy approach](https://mlsanity.com/paper/2101.07598/) (2021)
- [Sentiment and structure in word co-occurrence networks on Twitter](https://mlsanity.com/paper/2110.00587/) (2021)
- [Constructing dynamic residential energy lifestyles using Latent Dirichlet Allocation](https://mlsanity.com/paper/2204.10770/) (2022)
- [Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method](https://mlsanity.com/paper/2301.03029/) (2023)
- [Exploring the Power of Topic Modeling Techniques in Analyzing Customer Reviews: A Comparative Analysis](https://mlsanity.com/paper/2308.11520/) (2023)
- [TeCoMiner: Topic Discovery Through Term Community Detection](https://mlsanity.com/paper/2103.12882/) (2021)
- [Term-community-based topic detection with variable resolution](https://mlsanity.com/paper/2103.13550/) (2021)
- [A new system for evaluating brand importance: A use case from the fashion industry](https://mlsanity.com/paper/2106.14657/) (2021)
- [Unraveling the graph structure of tabular data through Bayesian and spectral analysis](https://mlsanity.com/paper/2110.01421/) (2021)
- [TSM: Measuring the Enticement of Honeyfiles with Natural Language Processing](https://mlsanity.com/paper/2203.07580/) (2022)
- [Revealing Patient-Reported Experiences in Healthcare from Social Media using the DAPMAV Framework](https://mlsanity.com/paper/2210.04232/) (2022)
- [More Data Types More Problems: A Temporal Analysis of Complexity, Stability, and Sensitivity in Privacy Policies](https://mlsanity.com/paper/2302.08936/) (2023)
- [Discovering Significant Topics from Legal Decisions with Selective Inference](https://mlsanity.com/paper/2401.01068/) (2024)
- [E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time](https://mlsanity.com/paper/2506.07747/) (2025)
- [Return migration of German-affiliated researchers: Analyzing departure and return by gender, cohort, and discipline using Scopus bibliometric data 1996-2020](https://mlsanity.com/paper/2110.08340/) (2021)
- [Graph2topic: an opensource topic modeling framework based on sentence embedding and community detection](https://mlsanity.com/paper/2304.06653/) (2023)
- [Use of explicit replies as coordination mechanisms in online student debate](https://mlsanity.com/paper/2311.18466/) (2023)
- [Probabilistic emotion and sentiment modelling of patient-reported experiences](https://mlsanity.com/paper/2401.04367/) (2024)
- [The Spectral Barycentre of a Set of Graphs with Community Structure](https://mlsanity.com/paper/2502.00038/) (2025)
- [Persistent Homology of Topic Networks for the Prediction of Reader Curiosity](https://mlsanity.com/paper/2506.11095/) (2025)

## Abstract (arXiv)

One of the main computational and scientific challenges in the modern age is to extract useful information from unstructured texts. Topic models are one popular machine-learning approach which infers the latent topical structure of a collection of documents. Despite their success --- in particular of its most widely used variant called Latent Dirichlet Allocation (LDA) --- and numerous applications in sociology, history, and linguistics, topic models are known to suffer from severe conceptual and practical problems, e.g. a lack of justification for the Bayesian priors, discrepancies with statistical properties of real texts, and the inability to properly choose the number of topics. Here we obtain a fresh view on the problem of identifying topical structures by relating it to the problem of finding communities in complex networks. This is achieved by representing text corpora as bipartite networks of documents and words. By adapting existing community-detection methods -- using a stochastic block model (SBM) with non-parametric priors -- we obtain a more versatile and principled framework for topic modeling (e.g., it automatically detects the number of topics and hierarchically clusters both the words and documents). The analysis of artificial and real corpora demonstrates that our SBM approach leads to better topic models than LDA in terms of statistical model selection. More importantly, our work shows how to formally relate methods from community detection and topic modeling, opening the possibility of cross-fertilization between these two fields.