What is it about?
Topic Models forms the group of words semantically relevant to the specific subject or theme. So a topic is a set of words with their likelihood in that topic. It also finds the proportion of different topics in the document. This paper surveys the topic modeling in a variety of ways, including domain-specific, parallel settings, tools, and technology. It also discusses the research challenges and future directions.
Featured Image
Photo by Sebastian Unrau on Unsplash
Why is it important?
We have been experiencing information overload due to the ever-expanding usage of the Internet through different types of applications. One should understand such an enormous collection of information without going through them. We can discover the hidden topics from such a large collection using topic modeling in an unsupervised manner. It is indeed a novel idea if one could search the information based on the theme, instead of the keyword. The topic model provides a cluster of semantically relevant words to do so.
Perspectives
This article aims to provide a survey covering variations and extensions of topic modeling techniques using Latent Dirichlet Allocation. It gives exposure to topic modeling research with respect to time, tools, and technology. I hope readers would find it interesting as it has been organized in a very abstract way, through interactive at the same time. Researchers can get insight very easily as each section incorporates the information in tabular format.
Dr. Uttam Chauhan
Vishwakarma Government Engineering College
Read the Original
This page is a summary of: Topic Modeling Using Latent Dirichlet allocation, ACM Computing Surveys, September 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3462478.
You can read the full text:
Contributors
The following have contributed to this page
