The field of app user feedback analysis is moving towards leveraging large language models and context-aware approaches to improve the classification and extraction of user feedback. Researchers are exploring the use of advanced language models, such as GPT-3.5-Turbo and GPT-4, to enhance user feedback classification and address the challenge of limited labeled datasets. Additionally, novel frameworks and approaches, such as Seq2seq and Natural Language Inference, are being proposed to extract software requirements and identify ethical concerns from app reviews. These innovations have the potential to significantly improve the accuracy and efficiency of user feedback analysis, enabling developers to better understand user needs and concerns. Noteworthy papers in this area include:

• Leveraging Large Language Models for Classifying App Users' Feedback, which evaluates the capabilities of advanced LLMs to enhance user feedback classification.
• SAGE: A Context-Aware Approach for Mining Privacy Requirements Relevant Reviews from Mental Health Apps, which introduces a context-aware approach to automatically mining privacy reviews from mental health apps.