Automating Knowledge Extraction: The Impact of Machine Learning on Text Mining Techniques
Cian Ramadhona Hassolthine, Ucuk Darusalam, Muhammad Ikhwani Saputra, Fenina Adline Twince Tobing, Muhamad Bahrul Ulum, Novi Dian Nathasia · 2024
This research investigates the transformative role of machine learning (ML) in automating knowledge extraction (AKE) from unstructured text data, a critical challenge in the era of big data. As organizations increasingly rely on vast amounts of textual information, the need for efficient and accurate extraction methods has become paramount. This study explores various ML techniques employed in text mining, including natural language processing (NLP), information retrieval (IR), and information extraction (IE), which collectively enhance the ability to convert unstructured data into structured knowledge. This study explores the application of Support Vector Machine (SVM) and XGBoost methods in sentiment analysis related to boycotted product campaigns using Twitter data collected from January 1 to June 30, 2024. This study aims to assess the effectiveness of both algorithms in classifying positive, neutral, and negative sentiments and evaluate their performance in this context. The results of the study show that XGBoost consistently outperforms SVM in various data sharing scenarios. This study provides valuable insights into how machine learning-based sentiment analysis can be used to understand public perceptions of companies in boycott cases and suggests a superior approach for similar future applications.