Content-boosted collaborative filtering for improved recommendations

By Prem Melville, Raymond J. Mooney, R. Nagarajan. 2002

1,378 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Image-Based Recommendations on Styles and Substitutes (2015, background): “Combinations of the two [3, 24] have been shown to help address the sparsity of the review”
Ask the GRU: Multi-task Learning for Deep Text Recommendations (2016, methodology): “Hybrid recommendation systems seek the best of both worlds, by leveraging both item content and user-item ratings [5, 10, 12, 13, 14].”
Social media recommendation based on people and tags (2010, methodology): “[23] present a hybrid recommender approach— Content-Boosted Collaborative Filtering (CBCF), which uses a CB predictor to enhance existing user data, and then provides personalized suggestions through CF.”
Terms of a Feather: Content-Based News Recommendation and Discovery Using Twitter (2011, background): “We may also provide a practical solution to the cold-start problem [13] of sparse profiles of users’ interests, an issue that has plagued many item discovery and recommender systems to date.”
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions (2005, methodology): “Moreover, several papers, such as [8], [65], [76], [100], empirically compare the performance of the hybrid with the pure collaborative and content-based methods and demonstrate that the hybrid methods can provide more accurate recommendations than pure approaches.”
Adaptive web search based on user profile constructed without any effort from users (2004, background): “[29] overcome drawbacks of collaborative filtering systems in their recommender system by exploiting content information of items already rated.”
Combining content-based and collaborative recommendations: A hybrid approach based on Bayesian networks (2010, methodology): “Some examples are [30,41,42] with the EachMovie dataset or [43,44,6,29] with MovieLens.”
Explaining Recommendations: Satisfaction vs. Promotion (2005, methodology): “However, for the full CBCF algorithm currently used by LIBRA, this would require recomputing every single user's content-based userprofile and re-scoring every item for every user to update the " filled in " user-item matrix.”
Do News Consumers Want Explanations for Personalized News Rankings (2017, background): “Collaborative ltering has been proven to be dicult to use for news recommendations due to what is known as the cold start or rst rater problem [7, 14].”
Partially Observable Markov Decision Process for Recommender Systems (2016, background): “Some tweaks, such as sampling for negative samples [15, 11] and/or neighborhood regularization [16], could make the RD phenomenon less severe.”
Alleviating the Sparsity Problem of Collaborative Filtering Using Trust Inferences (2005, background): “Item-based [12, 13] in addition to Content-boosted CF [13, 14] approaches require additional information regarding items as well as a metric to compute meaningful similarities among them [25].”
Recommender systems survey (2013, background): “[157] propose to add predictions from the CBF into the ratting matrix employed by the CF.”
Hybrid Web Recommender Systems (2007, background): “This is Melville's "content-boosted collaborative filtering" [30].”
MovieLens unplugged: experiences with an occasionally connected recommender system (2003, background): “Fab, and other systems like it have helped users find web pages, news articles, and other documents online [1, 4, 8].”
Content-Based News Recommendation (2010, background): “These two approaches are widely used and mixed together, which usually brings better results [9], [3].”