<![CDATA[The rapid development of information technology has had a significant impact on the spread of information, especially through social media. However, this convenience also brings challenges in the form of spreading fake news or hoaxes that can affect public perception and disrupt social stability. This study aims to develop an Indonesian text classification system to identify hoax news by using Word2Vec method as word representation technique and K-Nearest Neighbor (KNN) algorithm as its classification method. Word2Vec is used to convert text into numerical vectors representing the semantic meaning of words, so it can be used in the classification process. Meanwhile, the KNN algorithm is used to classify text into hoax or non-hoax categories based on feature similarity. The dataset used consists of 60 Indonesian-language news stories taken from turnbackhoax.id and detik.com . The evaluation results show that the combination of Word2Vec and KNN can provide a fairly good classification performance, with an accuracy rate of 76.92%. This study shows that Word2Vec and KNN approaches are effective for hoax news identification tasks, as well as potentially being further developed in application-based fake news detection systems. This finding is expected to contribute to efforts to improve digital literacy and community empowerment in dealing with misleading information in the digital era.]]>
Copyrights © 2026
