<![CDATA[There are numerous Indonesian YouTube channels with educational themes and a range of topics. However, a study based on the correlation between the comments column, the title, and the video was done to assess the channel's quality. The goal of this research is to determine whether the educational-themed channel that has been chosen as the study's subject has a relevant emphasis and whether it is connected to any current titles. Data from YouTube comments that were scraped using Python are used in this investigation. Data pre-processing was done to clean up the data obtained from audience remarks in order to speed up the procedure. We test predictions for sentiment analysis using the SVM and Decision Tree algorithms. A dependable technique for grouping or summarizing a huge text is Latent Dirichlet Allocation. The Bag of Words approach is then used to turn the comments into a corpus by using them as tokens and vectorizing them. The topic will show up following the creation of the LDA model. The amount of match between the word fragment and the generated subject was then calculated using the coherence value. The best combination of subjects from each channel is then determined in order to get a better coherence value. An even distribution of subjects is produced using LDA.]]>
Copyrights © 2023
