Topic models with elements of neural networks: investigation of stability, coherence, and determining the optimal number of topics

Author:

Koltcov Sergei1,Surkov Anton1,Filippov Vladimir2,Ignatenko Vera1

Affiliation:

1. Laboratory for Social and Cognitive Informatics, National Research University Higher School of Economics, Saint-Petersburg, Russia

2. Scientific Research Institute for Optoelectronic Instrument Engineering, Sosnovy Bor, Leningrad Region, Russia

Abstract

Topic modeling is a widely used instrument for the analysis of large text collections. In the last few years, neural topic models and models with word embeddings have been proposed to increase the quality of topic solutions. However, these models were not extensively tested in terms of stability and interpretability. Moreover, the question of selecting the number of topics (a model parameter) remains a challenging task. We aim to partially fill this gap by testing four well-known and available to a wide range of users topic models such as the embedded topic model (ETM), Gaussian Softmax distribution model (GSM), Wasserstein autoencoders with Dirichlet prior (W-LDA), and Wasserstein autoencoders with Gaussian Mixture prior (WTM-GMM). We demonstrate that W-LDA, WTM-GMM, and GSM possess poor stability that complicates their application in practice. ETM model with additionally trained embeddings demonstrates high coherence and rather good stability for large datasets, but the question of the number of topics remains unsolved for this model. We also propose a new topic model based on granulated sampling with word embeddings (GLDAW), demonstrating the highest stability and good coherence compared to other considered models. Moreover, the optimal number of topics in a dataset can be determined for this model.

Funder

“Modeling the structure and socio-psychological factors of news perception”

The Basic Research Program at the National Research University Higher School of Economics (HSE University) in 2022

Publisher

PeerJ

Subject

General Computer Science

Reference66 articles.

1. Constrained Clustering

2. Nonparametric spherical topic modeling with word embeddings;Batmanghelich,2016

3. Generalised information and entropy measures in physics;Beck;Contemporary Physics,2009

4. Variational inference for Dirichlet process mixtures;Blei;Bayesian Analysis,2006

5. Latent dirichlet allocation;Blei;Journal of Machine Learning Research,2003

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3