The field of personalized recommendation systems is rapidly evolving, with a focus on developing innovative models that balance relevance, diversity, and novelty. Recent research has explored the use of transformer-based architectures, graph neural networks, and multi-modal approaches to improve recommendation accuracy and user satisfaction. Notably, the incorporation of contextual and semantic features has led to significant advancements in recommendation systems. Furthermore, there is a growing emphasis on developing more sustainable and environmentally aware recommendation systems, which prioritize greenness and social responsibility. Overall, the field is moving towards more adaptive, exploration-based, and user-centric approaches, with a strong focus on evaluating and mitigating the impact of recommendation systems on society and the environment. Noteworthy papers include: Rankformer, which proposes a ranking-inspired recommendation model that leverages global information to produce more informative representations. Towards Carbon Footprint-Aware Recommender Systems, which introduces a dataset containing carbon footprint emissions for items and proposes a simple reranking approach to establish a better trade-off between accuracy and greenness.
Advances in Personalized Recommendation Systems
Sources
Earthquake Response Analysis with AI
ContextGNN goes to Elliot: Towards Benchmarking Relational Deep Learning for Static Link Prediction (aka Personalized Item Recommendation)
Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
Towards Carbon Footprint-Aware Recommender Systems for Greener Item Recommendation
Predicting Potential Customer Support Needs and Optimizing Search Ranking in a Two-Sided Marketplace
RAU: Towards Regularized Alignment and Uniformity for Representation Learning in Recommendation
Food Recommendation With Balancing Comfort and Curiosity
PRECTR: A Synergistic Framework for Integrating Personalized Search Relevance Matching and CTR Prediction
A Comprehensive Review on Hashtag Recommendation: From Traditional to Deep Learning and Beyond
Transformer-based Ranking Approaches for Keyword Queries over Relational Databases
Beyond Relevance: An Adaptive Exploration-Based Framework for Personalized Recommendations
Fully personalized PageRank and algebraic methods to distribute a random walker
FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies
An NLP-Driven Approach Using Twitter Data for Tailored K-pop Artist Recommendations
Behavioral response to mobile phone evacuation alerts
Risk-Prone and Risk-Averse Behavior in Natural Emergencies: An Appraisal Theory Approach