<![CDATA[The rapid development of social media goes hand in hand with the increase in social media users. Among the social media platforms widely used in Indonesia, Twitter is one of the most popular. On Twitter, users are free to share every moment they experience or what they think. Many users use Twitter as a medium to express their emotions, as is what happens in angry communities. There are no special requirements to join as a community member other than getting admin approval. This community provides a place for its members to vent all kinds of anger they feel. This research classifies angry community tweets to find out the types of problems in these tweets. The results of this research can help in understanding communication and behavior patterns in angry communities, which can provide deeper insight into the social dynamics within them.Text data is retrieved via web scraping techniques, and then processed through a series of preprocessing steps, including unnecessary character removal, normalization, and tokenization. The classification uses the Long Short-Term Memory (LSTM) algorithm with six problem category classes, namely Study, Romance, Family, Career/Work, Person/Personal, and Swearing. After modeling, the model accuracy was 91.94%. The model was built using an embedding layer, Long Short-Term Memory (LSTM) layer, dense layer, and dropout layer which was run for 10 epochs. Model evaluation is carried out using metrics such as accuracy, precision, recall, and F1-score to measure model performance. The value resulting from the evaluation results using the confusion matrix is more than 50, this indicates that the LSTM model is able to classify the problem well.]]>
