Semantic Similarity Measure for Topic Modeling Using Latent Dirichlet Allocation and Collapsed Gibbs Sampling

Author:

Ajinaja Micheal Olalekan1,Adetunmbi Olusola Adebayo1,Ugwu Chukwuemeka Christian1,Solomon Popoola Olugbemiga2

Affiliation:

1. Federal University of Technology Akure, Ondo

2. Osun State College of Education

Abstract

Abstract One of the key applications of Natural Language Processing (NLP) is to automatically extract topics from large volumes of text. Latent Dirichlet Allocation (LDA) technique is commonly used to extract topics based on word frequency from the pre-processed documents. A major issue of LDA is that the quality of topics extracted are poor if the document do not coherently discuss a single topic. However, Gibbs sampling uses word by word basis which changes the topic assignment of one word and can be used on documents having different topics. Hence, this paper proposed a hybrid based semantic similarity measure for topic modelling using LDA and Gibbs sampling to exploit the strength of automatic text extraction and improve coherence score. Unstructured dataset was obtained from a public repository to validate the performance of the proposed model. The evaluation carried out shows that the proposed LDA-Gibbs had a coherence score of 0. 52650 as against LDA coherence score 0.46504. The proposed multi-level model provides better quality of topics extracted.

Publisher

Research Square Platform LLC

Reference35 articles.

1. Lazarina (2021, July 1) Topic Modelling: A Deep Dive into LDA, hybrid-LDA, and non-LDA Approaches.https://lazarinastoy.com/topic-modelling-lda/

2. Jonsson E. and Stolee J. An Evaluation of Topic Modelling Techniques for Twitter. An evaluation of topic modelling techniques for Twitter. (n.d.). Retrieved August 7, 2022, from https://www.cs.toronto.edu/jstolee/projects/topic.pdf

3. Xing Yi and James Allan. A comparative study of utilizing topic models for information retrieval. In Advances in Information Retrieval, pages 29–41. Springer, 2009.

4. Jianshu Weng, Ee-Peng Lim, Jing Jiang, and Qi He. Twitterrank: finding topic-sensitive influential twitterers. In Proceedings of the third ACM international conference on Web search and data mining, pages 261–270. ACM, 2010

5. Philip Resnik, William Armstrong, Leonardo Claudino, Thang Nguyen, Viet-An Nguyen, and Jordan Boyd-Graber. Beyond lda: exploring supervised topic modeling for depression-related language in twitter. NAACL HLT 2015, page 99, 2015.

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