Infusing Collaborative Recommenders with Distributed Representations

Abstract

Recommender systems assist users in navigating complex information spaces and focus their attention on the content most relevant to their needs. Often these systems rely on user activity or descriptions of the content. Social annotation systems, in which users collaboratively assign tags to items, provide another means to capture information about users and items. Each of these data sources provides unique benefits, capturing different relationships.In this paper, we propose leveraging multiple sources of data: ratings data as users report their affinity toward an item, tagging data as users assign annotations to items, and item data collected from an online database. Taken together, these datasets provide the opportunity to learn rich distributed representations by exploiting recent advances in neural network architectures. We first produce representations that subjectively capture interesting relationships among the data. We then empirically evaluate the utility of the representations to predict a user's rating on an item and show that it outperforms more traditional representations. Finally, we demonstrate that traditional representations can be combined with representations trained through a neural network to achieve even better results.

Information Fusion-Based Deep Neural Attentive Matrix Factorization Recommendation

“…), to improve performance of recommendation systems of the model. Furthermore, Greg Zanotti et al [21] employed the neural network language model to fuse information from multiple sources, including user data, item data, and tag data, to extract rich feature representations of users and items.…”

Automatic extraction of informal topics from online suicidal ideation

“…Examples of language models include simple bag-of-word models [ 16 ] and extend to more robust models such as probabilistic latent semantic analysis [ 17 ], latent dirichlet allocation [ 18 ], and Word2Vec [ 19 , 20 ]. Such language models have been used to explore numerous topics such as comparing topics in data [ 21 ], recommendation systems [ 22 ], and different languages [ 23 ]. We focus on the Word2Vec language model developed by Mikolov et al [ 19 , 20 ].…”