Effective Machine Learning Garbage Data Filtering Algorithm for SNS Big Data Processing

Abstract

Social network services (SNS) are used more often today, which results in more SNS data being generated. Furthermore, greater emphasis is being placed on extracting various sorts of information through the collection, processing, and analysis of massive volumes of SNS data. Although big data processing can extract a lot of information from SNS data, it takes a long time and a lot of resources. As a result, gaining insights from SNS data necessitates a significant investment of time and money. In this section, we propose a data filtering approach for removing unnecessary SNS data from the data stream. To improve filtering accuracy, the suggested method employs Random Forest, Decision Tree, and XGBoost. Research shows that the suggested algorithm filters the experimental keywords by more than 70%.