Loading...
MoodMate: Emotion-Driven Personalized Movie Recommendation System
Alahmadi, Jood Alshareef, Sarah Moathen, Albatool
Alahmadi, Jood
Alshareef, Sarah
Moathen, Albatool
Citations
Altmetric:
Type
Supervisor
Date
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
This project presents the development of an innovative emotion-based movie recom-
mendation website that utilizes advanced sentiment analysis techniques to personalize
film suggestions for individual users. Rooted in the interdisciplinary fields of affec-
tive computing, emotional psychology, and human-computer interaction, the system
is designed to recognize and interpret the emotional states of users, using this infor-
mation to tailor recommendations that align with or intentionally contrast the user’s
mood. Drawing upon psychological principles such as mood-congruent memory and
emotional regulation, the platform enhances viewer engagement by suggesting films
that resonate emotionally or provide mood-lifting alternatives, thereby enriching the
user’s entertainment experience.
In contrast to conventional recommendation systems that primarily rely on user be-
havior, genre preferences, or collaborative filtering, this approach uniquely integrates
emotional input as a central factor in decision-making. The system not only offers rec-
ommendations that are more psychologically attuned but also ensures a level of trans-
parency and fairness in AI-driven processes. By dynamically adapting its suggestions
based on real-time emotional feedback, the platform maintains relevance and respon-
siveness throughout user interaction.
A key feature of the system is an interactive chatbot that engages users in natural
language conversation, asking reflective questions to gauge emotional context and en-
tertainment preferences. This conversational interface not only improves data collection
but also contributes to a more personalized and human-like user experience. The emo-
tional data gathered is processed through sentiment analysis algorithms that classify and
respond to nuanced user moods, making the system both intelligent and empathetic.
With the potential for seamless integration into existing streaming services and dig-
ital entertainment platforms, this emotion-aware recommendation system represents a
transformative step in how content is discovered and consumed. By aligning movie
suggestions with users’ emotional states, the system aspires to increase viewer satisfac-
tion, foster emotional resonance, and ultimately redefine user interaction in the digital
entertainment landscape