International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Leveraging Movie Recommendation Using Facial Emotion Anamika Pandey1, Manisha Kumari2, Harsh Dubey3, Dr. Nidhi Gupta 4 123Student, Department of Computer Science, Sharda University & Greater Noida (UP), India
4Associate Professor, Department of Computer Science, Sharda University & Greater Noida (UP), India
---------------------------------------------------------------------***--------------------------------------------------------------------goes much beyond traditional paradigms. A more realistic Abstract - An emotion-based movie recommendation system suggests movies that are appropriate based on the persons emotion. It's like having a friend who knows just what movie will make you happy when you're depressed or What would give you a nice scare if you were in the mood for it. This improves your movie-watching experience by increasing the likelihood of finding something that precisely matches your present mood. This research paper explores movie recommendations on the basis of facial emotions. It aims to analysis face expressions in real-time and also by the image and suggest movies according to the emotions. For Example if you are feeling sad, this system will provides you movies that will make your mood happy. The system uses python, Machine Learning Libraries, Deep Learning Models, Web Development Frameworks, APIs. The study tackles emotion representation, data collecting, and algorithmic design while navigating the complex relationship between emotions and movie choices. The results highlight how well the system responds to users' present emotional states to increase user pleasure and engagement.
and emotionally meaningful movie viewing experience is promised by the system's dynamic responsiveness to users' emotional states, which can transform digital content distribution andelevate customer engagement on streaming services. Our methodology's fundamental component is the real-time facial expression analysis through the analysis of facial information, the system is able to get a sophisticated knowledge of viewers' emotional states and provide a basis for movie suggestions that are in line with their present mood.
Key Words: Movie Recommendation System1, Machine Learning Algorithms2, Facial expression Analysis3, Recommendation Algorithms4, Personalized Movies Recommendations5 etc.
A. Recommendation systems that consider
2. LITERATURE REVIEW A fundamental change in the field of movie recommendations has taken place, with an increasing focus on emotion-aware algorithms that challenge conventional models that mostly depend on past user preferences. A growing body of research has shown how important it is to include human emotions in the recommendation process. emotions. Li et al. (2022) [1] explore deep learning for emotion detection in user-generated content for more precise suggestions considering emotion. This aligns with Wu et al.'s (2021) discovery emphasizing real- time emotion analysis to improve recommendation algorithm efficiency.
1.INTRODUCTION The study presents a movie recommendation system. The system is based on the user's emotions. The movie is a very significant element of our lives. People watch movies to relieve their tension. Movies are an essential aspect of our lives. People watch films on a daily basis to relieve stress and learn something new. The fundamental issue is that consumers are often unable to select appropriate movies based on their mood or emotion. The emotion can be any such as happy, sad, angry surprised, or excited. In the constantly developing domain of digital entertainment, this study explores the cutting- edge field of "Emotion-Based Movie recommendations" Unlike traditional recommendation systems, our method includes real-time facial expression analysis made possible by sophisticated proposed methodology that is implemented in python language. The many complexities of human emotions are frequently difficult for traditional models to represent, which limits how personalized the content recommendations can be. By presenting a cutting- edge technology that can understand users' emotionsfrom camera-captured facial expressions, this study seeks to close this gap. The applicability of this study
© 2024, IRJET
|
Impact Factor value: 8.226
B. NLP Methods for Emotional Analysis.
NLP, exemplified in research by Chen et al. (2023) [2], enables understanding of textual and visual emotional cues. Sophisticated NLP algorithms effectively analyze user generated reviews, extracting emotional context for discerning movie suggestions. C. Facial Expression Analysis in Real-Time:
Smith et al. (2023) [3] advance real-time facial expression analysis using deep learning for emotion identification. This research contributes to creating systems that adjust movie suggestions based on users' current emotional states, leveraging improvements in computer vision.
|
ISO 9001:2008 Certified Journal
|
Page 1145