# Computational thematics: Comparing algorithms for clustering the genres of literary fiction

arXiv: https://arxiv.org/abs/2305.11251 · HTML: https://mlsanity.com/paper/2305.11251/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 76 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 14 of 14)

- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Top2Vec: Distributed Representations of Topics](https://mlsanity.com/paper/2008.09470/) (2020)
- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation](https://mlsanity.com/paper/1607.05368/) (2016)
- [A network approach to topic models](https://mlsanity.com/paper/1708.01677/) (2017)
- [Bayesian cluster analysis: Point estimation and credible balls](https://mlsanity.com/paper/1505.03339/) (2015)
- [Why Moli`ere most likely did write his plays](https://mlsanity.com/paper/2001.01595/) (2020)
- [Topic Modeling Genre: An Exploration of French Classical and Enlightenment Drama](https://mlsanity.com/paper/2103.13019/) (2021)
- [Relative contributions of Shakespeare and Fletcher in Henry VIII: An Analysis Based on Most Frequent Words and Most Frequent Rhythmic Patterns](https://mlsanity.com/paper/1911.05652/) (2019)
- [Semantics of European poetry is shaped by conservative forces: The relationship between poetic meter and meaning in accentual-syllabic verse](https://mlsanity.com/paper/2109.07148/) (2021)
- [Fashion and art cycles are driven by counter-dominance signals of elite competition: quantitative evidence from music styles](https://mlsanity.com/paper/1901.03114/) (2019)

## Built on by (most cited first, 5 of 5)

- [Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence](https://mlsanity.com/paper/2309.14379/) (2023)
- [Latent Structures of Intertextuality in French Fiction](https://mlsanity.com/paper/2410.17759/) (2024)
- [Locating the Leading Edge of Cultural Change](https://mlsanity.com/paper/2411.15068/) (2024)
- [Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes](https://mlsanity.com/paper/2505.23166/) (2025)
- [FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction](https://mlsanity.com/paper/2510.20926/) (2025)

## Abstract (arXiv)

What are the best methods of capturing thematic similarity between literary texts? Knowing the answer to this question would be useful for automatic clustering of book genres, or any other thematic grouping. This paper compares a variety of algorithms for unsupervised learning of thematic similarities between texts, which we call "computational thematics". These algorithms belong to three steps of analysis: text preprocessing, extraction of text features, and measuring distances between the lists of features. Each of these steps includes a variety of options. We test all the possible combinations of these options: every combination of algorithms is given a task to cluster a corpus of books belonging to four pre-tagged genres of fiction. This clustering is then validated against the "ground truth" genre labels. Such comparison of algorithms allows us to learn the best and the worst combinations for computational thematic analysis. To illustrate the sharp difference between the best and the worst methods, we then cluster 5000 random novels from the HathiTrust corpus of fiction.