<p>One of the main problems in the knowledge discovery field is extracting interesting patterns from datasets to obtain useful knowledge. The knowledge discovery process involves Data Mining (DM) as a fundamental step, which produces an extensive range of rules. However, some of these rules are not useful for decision-makers. Among DM techniques, Association Rule Mining (ARM) plays a crucial role in uncovering hidden and meaningful relationships between data items, forming the foundation for decision-making and knowledge discovery. Interestingness measures should be part of the process of extracting interesting rules from the data. These measures filter and rank rules based on their potential interest to the users. Good measures also allow for a decrease in the time and space expenses associated with mining. Interestingness measures are classified into objective and subjective categories. While rule mining identifies patterns, interestingness measures help determine which are most valuable to decision-makers. This survey provides a comprehensive review and classification of ARM measures, including fundamental, advanced, and extended objective measures, multi-objective optimization approaches, and subjective (user-driven) measures. It highlights their theoretical foundations, strengths, limitations, applications, and comparative performances. Furthermore, the survey identifies gaps and challenges, such as scalability, interpretability, and integration of user knowledge, and proposes future research directions focused on hybrid, adaptive, and interpretable ARM frameworks. This survey serves as a reference point for understanding the relationship between rule mining and interestingness evaluation and highlights areas requiring further validation and exploration to strengthen the generalizability and practical adoption of these measures.</p>