<![CDATA[The advancement of digital technology has driven the emergence of various innovations in delivering personalized entertainment content. One promising approach is a mood-based recommendation system, which enables users to receive suggestions for movies or music that match their emotional state. This study designed and developed VibeScreen, a prototype application for recommending movies and music based on user mood using sentiment analysis of text inputs. The system applies Natural Language Processing (NLP) techniques to classify user sentiment, which is then used to generate relevant entertainment recommendations. The application was developed using Flutter for the mobile interface and Flask for the backend services, with Firebase supporting user authentication and data storage. The dataset was collected through online questionnaires and secondary sources such as IMDb and Spotify. Testing results show that the system can provide mood-relevant recommendations with an interactive and responsive interface. This research contributes by integrating movies and music recommendations in a single platform, offering a more adaptive and emotionally relevant entertainment experience.]]>
Copyrights © 2025
