Open AccessEmotion-based Media Recommendation System
Author(s) -
Shailendra S. Aote,
Aayush Muley,
Adesh Kotgirwar,
Yash Daware,
Gaurav Shukla,
Jayesh Kapse
Publication year - 2021
Publication title -
international journal of next-generation computing
Language(s) - English
Resource type - Journals
eISSN - 2229-4678
pISSN - 0976-5034
DOI - 10.47164/ijngc.v12i5.415
Subject(s) - mood , face (sociological concept) , computer science , digital media , facial expression , recommender system , emotion detection , psychology , emotion recognition , mental state , state (computer science) , classifier (uml) , emotional intelligence , multimedia , artificial intelligence , cognitive psychology , social psychology , machine learning , world wide web , sociology , social science , algorithm
In today’s world, digital media is a significant element of human life. People take its help to stay motivated and explore media according to their moods. It takes a lot of effort to find appropriate music that suits the particular emotional state from loads of options available. Media players in today’s world are not giving priority to the emotional state and effective recommendation of a person. Human emotion plays a vital role in media selection in recent times. Emotion expresses the individual’s behavior and state of mind and digital media has the power to change one’s mental state from negative to positive. The objective of this paper is to extract features from the human face and detect emotion, age, and gender, and suggest media according to the features detected. The emotional state, age, and gender can be interpreted from facial expressions through the webcam. We have used the CNN classifier to build a neural network model. This model is trained and subjected to detect mood, age, and gender from facial expressions using OpenCV. A system that generates a media playlist based on the detected emotion, age, and gender gives better results.