ANALYSIS OF THE RELATIONSHIP BETWEEN SEIYUU POPULARITY AND ANIME USING THE WEB SCRAPING DATA RETRIEVAL METHOD ON THE MYANIMELIST.NET SITE

Abstract

Today, enormous volumes of data are generated every day at an unprecedented speed from various sources, including data on the internet. The existence of the internet makes the amount of data contained on the website increase, so we need an efficient method to collect a lot of data on a website, and web scraping is one of them. In this study, the researchers implemented the web scraping method on the myanimelist.net site which is the largest community and database of anime and manga in the world. The purpose of this study is to analyze the relationship between the seiyuu (voice actors) and the anime they play through correlation. This research method broadly consists of five stages, including data extracting, data cleansing, data processing, statistical testing, and data visualization. The research tools used for scraping are beautifulsoup and pandas which are python libraries, while the tools for processing and analyzing scraping data are collaborative google and pandas which are data processing applications. The results of this study indicate that web scraping can be implemented on the myanimelist.net site effectively. Researchers were able to collect 54298 rows of data from 275 people within 8 days. The results of the analysis show that the popularity of seiyuu has a moderate relationship with the popularity of the characters they play and the number of anime they play.. Keywords : big data, web scraping, anime