<![CDATA[Clickbait is a strategy commonly used to attract readers' attention with promising sensational or intriguing headlines. However, often these clickbait headlines do not correspond to the actual content of the news, resulting in disappointment for the readers. Therefore, this study aims to classify clickbait news headlines in the Indonesian language using the K-Nearest Neighbors (K-NN) method. The purpose of this research is to evaluate the ability of the K-NN method to classify clickbait news headlines in the Indonesian language. Thus, it is expected to provide a better understanding of the effectiveness of this method in identifying clickbait headlines. This study utilizes the K-NN method to classify clickbait news headlines. The data consists of 800 training data and 200 test data. The training and testing processes are conducted by varying the number of neighbors (k) and using various supporting features. The results show that the best performance of the K-NN method is achieved with a number of neighbors k=11, yielding an accuracy of 80.5%, Precision of 85%, Recall of 81%, and F-measure of 80%. Testing with 20 new data also resulted in an accuracy rate of 90%. Additionally, several unique words that frequently appear in clickbait headlines are identified, such as "apa" (what), "kenapa" (why), "nih" (here), "alasan" (reason), and "wow". This research contributes to identifying clickbait news headlines in the Indonesian language using the K-NN method. The findings of this study can serve as a reference for further research and provide better insights into how the K-NN method can be applied in classifying clickbait headlines.]]>
