@article {10.3844/jcssp.2024.1734.1743,
article_type = {journal},
title = {Comparative Analysis of Topic Modeling on People Query-Based Data},
author = {M, Saranya and B, Amutha},
volume = {20},
number = {12},
year = {2024},
month = {Nov},
pages = {1734-1743},
doi = {10.3844/jcssp.2024.1734.1743},
url = {https://thescipub.com/abstract/jcssp.2024.1734.1743},
abstract = {As using the internet becomes more common in our daily lives, Perhaps greater numbers of individuals are buying things digitally. Specialized digital marketplaces for things like clothes and books have turned into megastores with many stores. This makes it harder to find what you're looking for and takes more time. The query's data content is estimated ahead of time from the query logs and usually includes one or more search terms. Classifying the changes that users make to the information in their query strings is one way to model how they search. The article explains how to use topic modeling to effectively pull out product behavior patterns from data. An effective and flexible topic modeling tool is used to create the final models. Lots of different models can be tested with this framework, including PLSA, LDA, PAM, NMF, LSA, and many more. The results show that the technique can gather data on the different ways that people use a certain product. In order to deal with this kind of problem, we were able to come up with a strong solution using topic modeling. Topic modeling clearly assisted with the categorization of the product review. PLSA does better than the topic models suggested by NMF and LDA, according to the results.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}