Genre-aware user profiling using duration count matrices: A novel approach to enhancing content recommendation systems

Recommender systems play a vital role in enhancing the user experience and facilitating content discovery on online platforms. However, conventional approaches often struggle to capture users' evolving preferences over time, leading to suboptimal performance as recommended videos frequently do not align with users' interests. To address this issue, this study introduces an innovative method that leverages watch-time duration to analyze long-term user behavior and generate personalized recommendations. The proposed Duration Count Matrix (DCM) technique includes two key components: User Profiling (DCM-UP) and User Similarity (DCM-US). DCM-UP constructs dynamic user profiles based on engagement with content, while DCM-US quantifies user similarity through collaborative filtering, enabling the system to predict user-to-user behavior and personalize recommendations. This innovative system, DCM-UP, utilizes matrix-based representations of users and items, dynamically updates profiles, and adapts to changing preferences over time, thus providing a more accurate reflection of user interests. Additionally, DCM-US facilitates the identification of user similarities by analyzing user-item generalizations. Moreover, the effectiveness of the proposed techniques was evaluated on a real-world dataset obtained from JAWWY, the Saudi Telecom Company. The study's results clearly demonstrated that the DCM approach significantly outperformed existing state-of-the-art methods across various performance metrics, including precision, recall, F1-score, and accuracy. This highlights the superiority of the DCM technique in capturing and predicting long-term user behavior for more accurate and personalized recommendations.