Fab: content-based, collaborative recommendation

By Marko Balabanovic, Yoav Shoham. 1997

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

Explainable Recommendation: A Survey and New Perspectives (2018, background): “Content-based recommender systems attempt to model user and/or item profiles with various available content information, such as the price, color, brand of the goods in e-commerce, or the genre, director, duration of the movies in review systems (Balabanović and Shoham [1997], Pazzani and Billsus [2”
Ask the GRU: Multi-task Learning for Deep Text Recommendations (2016, methodology): “Content-based methods [8, 9], on the other hand, use the item text or attributes, and make recommendations based on similarity between such attributes, ignoring data from other users.”
A Framework for Collaborative, Content-Based and Demographic Filtering (1999, background): “advocated by Billsus and Pazzani (1998) as an alternative to the collaboration via content approach proposed here for addressing the sparse matrix problem.”
Efficient Adaptive-Support Association Rule Mining for Recommender Systems (2004, background): “…a technology that allows personalized recommendations of items of potential interest to users based on information ∗Corresponding author. about similarities and dissimilarities among different users’ tastes (see e.g. Shardanand and Maes, 1995; Resnick et al., 1994; Balabanovic and Shoham, 1997).”
Recommender Systems (2012, background): “…and content-based methods and then combine their predictions [162,163]; (ii) add content-based characteristics to collaborative models [164–166]; (iii) add collaborative characteristics to content-based models [167] and (iv) develop a general unified model that integrate both…”
Learning Image and User Features for Recommendation in Social Networks (2015, background): “CBF recommends images based on a comparison between the contents of the images and a user profile [2, 26].”
Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering (2004, background): “Researchers have also attempted to combine collaborative filtering with contentbased recommendation approaches to alleviate the sparsity problem [Balabanovic and Shoham 1997; Basu et al. 1998; Condliff et al. 1999; Good et al. 1999; Huang et al. 2002; Pazzani 1999; Sarwar et al. 1998].”
Music recommendation and discovery in the long tail (2008, methodology): “Normalised distance-based performance (NDPM) was introduced in (Balabanovic and Shoham, 1997) to evaluate their collaborative filtering recommender system, named FAB.”
Hybrid Recommender Systems: Survey and Experiments (2002, methodology): “Recommender systems were originally defined as ones in which ’people provide recommendations as inputs, which the system then aggregates and directs to appropriate recipients’ [1].”
Expertise recommender: a flexible recommendation system and architecture (2000, methodology): “Recommendation systems have been used to recommend a variety of things including Usenet news [11], web pages [ 2 , 9], videos [8], movies, music [18] and books.”
A personalized recommender system based on web usage mining and decision tree induction (2002, unknown): “To date, a variety of recommendation techniques (Balabanović & Shoham, 1997; Basu, Hirsh, & Cohen, 1998; Hill, Stead, Rosenstein, & Furnas, 1995; Lawrence, Almasi, Kotlyar, Viveros, & Duri, 2001; Resnick, Iacovou, Suchak, Bergstrom, & Riedl, 1994; Sarwar, Karypis, Konstan, & Riedl, 2001;…”
A generalized taxonomy of explanations styles for traditional and social recommender systems (2012, methodology): “To overcome this limitation, several recommender systems have proposed the combination of content data with rating data (Balabanovic and Shoham 1997; Jin 2005; Melville et al. 2002; Salter and Antonopoulos 2006).”
Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques (2012, background): “Recommender systems are usually classified into three categories based on their approach to recommendation: content-based, collaborative, and hybrid approaches [1], [3].”
Social contextual recommendation (2012, methodology): “[27] combine collaborative filtering and content-based filtering [1] which selects items based on the correlation between the contents of items and preferences of users.”
Improving recommendation lists through topic diversification (2005, methodology): “Less frequently used, NDPM [2] compares two diﬀerent, weakly ordered rankings.”
Short and tweet: experiments on recommending content from information streams (2010, methodology): “Prior works [ 4 , 12] have demonstrated the effectiveness of combining text content from a user group to capture the interest of single user, although their motivation is to solve the coldstart problem and the data sparsity problem and not to model a different type of interest.”