PROJECT TITLE :
Scalable Content-Aware Collaborative Filtering for Location Recommendation - 2018
Location recommendation plays an essential role in serving to folks realize enticing places. Though recent research has studied the way to advocate locations with social and geographical data, few of them addressed the cold-start downside of latest users. Because mobility records are typically shared on social networks, semantic info will be leveraged to tackle this challenge. A typical technique is to feed them into express-feedback-based content-aware collaborative filtering, however they require drawing negative samples for better learning performance, as users' negative preference is not observable in human mobility. However, previous studies have empirically shown sampling-based methods don't perform well. To this finish, we tend to propose a scalable Implicit-feedback-based Content-aware Collaborative Filtering (ICCF) framework to incorporate semantic content and to avoid negative sampling. We tend to then develop an efficient optimization algorithm, scaling linearly with information size and feature size, and quadratically with the dimension of latent house. We have a tendency to additional establish its relationship with graph Laplacian regularized matrix factorization. Finally, we evaluate ICCF with a large-scale LBSN dataset in that users have profiles and textual content. The results show that ICCF outperforms many competing baselines, which user information isn't solely effective for improving recommendations but conjointly coping with cold-start scenarios.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here