EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LDAPrototype: a model selection algorithm to improve reliability of latent Dirichlet allocation

Jonas Rieger, Carsten Jentsch, Jörg Rahnenführer

PeerJ Computer Science · 20.09.2024 · 10 · e2279

DOI: 10.7717/peerj-cs.2279 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 20.09.2024. Verfasst von Jonas Rieger und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, TU Dortmund University, Dortmund, Germany. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Linux HPC cluster at TU Dortmund University, The Large-Scale Equipment Initiative by the German Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Latent Dirichlet allocation (LDA) is a popular method for analyzing large text corpora, but it suffers from instability due to its reliance on random initialization. This results in different outcomes for replicated runs, hindering reproducibility. To address this, we introduce LDAPrototype, a new approach for selecting the most representative LDA run from multiple replications on the same dataset. LDAPrototype enhances the reliability of LDA conclusions by ensuring greater similarity between replications compared to traditional LDA runs or models chosen based on perplexity or NPMI. A key feature of LDAPrototype is its use of a novel model similarity measure called S-CLOP (Similarity of multiple sets by Clustering with LOcal Pruning). It is based on topic similarities, for which we compare the usage of measures like the thresholded Jaccard coefficient, cosine similarity, Jensen-Shannon divergence, and rank-biased overlap. The effectiveness of LDAPrototype is demonstrated through its application to six real datasets, including newspaper articles and tweets. The results show improved reproducibility and reliability in topic modeling outcomes. LDAPrototype’s approach is noteworthy for its practical applicability, comprehensibility, ease of implementation, and computational efficiency. Furthermore, the algorithm’s concept can be generalized to other topic modeling procedures that characterize topics through word distributions, making it a versatile tool in text data analysis.

Schlagwörter

Stichwörter der Autor:innen

ClusteringMedoidReplicationsSimilarityStabilityTopic model

Autor:innen und Institutionen

  • Department of Statistics, TU Dortmund University, Dortmund, Germany.

Förderung

  • The Linux HPC cluster at TU Dortmund University
  • The Large-Scale Equipment Initiative by the German Research Foundation

Zitieren

APA

Rieger, J., Jentsch, C., & Rahnenführer, J. (2024). LDAPrototype: a model selection algorithm to improve reliability of latent Dirichlet allocation. PeerJ Computer Science, 10, e2279. https://doi.org/10.7717/peerj-cs.2279

Vancouver

Rieger J, Jentsch C, Rahnenführer J. LDAPrototype: a model selection algorithm to improve reliability of latent Dirichlet allocation. PeerJ Computer Science. 2024;10:e2279. doi:10.7717/peerj-cs.2279

BibTeX
@article{Rieger2024,
  author = {Rieger, Jonas and Jentsch, Carsten and Rahnenführer, Jörg},
  title = {LDAPrototype: a model selection algorithm to improve reliability of latent Dirichlet allocation},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2279},
  doi = {10.7717/peerj-cs.2279}
}
Kostenlos starten →