Mining app reviews has emerged as a valuable practice in requirements engineering, providing insights into feature usage trends, user satisfaction, and emerging software issues. While recent advances in natural language processing have enhanced review analysis, challenges persist in feature extraction, sentiment ambiguity, and the scalability of automated methods, among others. This project report presents our research efforts in app review mining, focusing on methodological, software-based, and data-driven contributions. We explore both supervised and unsupervised learning approaches, leveraging large language models for key tasks such as feature identification, competition analysis, and emotion extraction. Additionally, we develop open-source tools and datasets to support reproducibility and adoption of our methods. Our findings highlight the potential of large language models in automating user feedback analysis while identifying gaps that require further research, particularly in addressing model reliability and evaluation challenges.