<![CDATA[The rapid growth of digital technology and social media has significantly influenced the dissemination of information and public opinion worldwide. YouTube, as one of the largest social media platforms, is widely used by users to express opinions on international issues, including geopolitical conflicts. One event that attracted substantial public attention was the reported downing of an Indian Rafale fighter jet by a Pakistani J-10CE within the context of the India–Pakistan conflict. This study aims to analyze public sentiment expressed in YouTube comments related to this incident using a Deep Learning approach based on the Long Short-Term Memory (LSTM) algorithm. A total of 1,336 English-language YouTube comments were collected using the YouTube Data API v3. The data were automatically labeled into three sentiment categories: positive (38.32%), negative (31.21%), and neutral (30.46%). The research process includes text preprocessing, sentiment labeling using VADER, LSTM model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. Experimental results show that the proposed model achieved an accuracy of 61% with a macro-averaged F1 score of 0.61 on the test set. These findings indicate that the model provides moderate and stable performance in analyzing sentiment within conflict-driven geopolitical discussions on social media]]>
Copyrights © 2026
