This paper focuses on inferring category-specific social trust circles from available rating data combined with social network data, and outlines several variants of weighting friends within circles based on their inferred expertise levels.
Abstract:
Online social network information promises to increase recommendation accuracy beyond the capabilities of purely rating/feedback-driven recommender systems (RS). As to better serve users' activities across different domains, many online social networks now support a new feature of "Friends Circles", which refines the domain-oblivious "Friends" concept. RS should also benefit from domain-specific "Trust Circles". Intuitively, a user may trust different subsets of friends regarding different domains. Unfortunately, in most existing multi-category rating datasets, a user's social connections from all categories are mixed together. This paper presents an effort to develop circle-based RS. We focus on inferring category-specific social trust circles from available rating data combined with social network data. We outline several variants of weighting friends within circles based on their inferred expertise levels. Through experiments on publicly available data, we demonstrate that the proposed circle-based recommendation models can better utilize user's social trust information, resulting in increased recommendation accuracy.
TL;DR: A survey of heterogeneous information network analysis can be found in this article, where the authors introduce basic concepts of HIN analysis, examine its developments on different data mining tasks, discuss some advanced topics, and point out some future research directions.
TL;DR: In this paper, a model-based method that adopts matrix factorization technique that maps users into low-dimensional latent feature spaces in terms of their trust relationship, and aims to more accurately reflect the users reciprocal influence on the formation of their own opinions and to learn better preferential patterns of users for high-quality recommendations.
TL;DR: This paper presents how social network information can be adopted by recommender systems as additional input for improved accuracy and surveys and compares several representative algorithms of collaborative filtering (CF) based socialRecommender systems.
TL;DR: Three social factors, personal interest, interpersonal interest similarity, and interpersonal influence, fuse into a unified personalized recommendation model based on probabilistic matrix factorization and results show the proposed approach outperforms the existing RS approaches.
TL;DR: Experimental results show that iGSLR provides significantly superior location recommendation compared to other state-of-the-art geo-social recommendation techniques.
TL;DR: This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches.
TL;DR: The Probabilistic Matrix Factorization (PMF) model is presented, which scales linearly with the number of observations and performs well on the large, sparse, and very imbalanced Netflix dataset and is extended to include an adaptive prior on the model parameters.
TL;DR: The factor and neighborhood models can now be smoothly merged, thereby building a more accurate combined model and a new evaluation metric is suggested, which highlights the differences among methods, based on their performance at a top-K recommendation task.
TL;DR: This paper shows how a class of two-layer undirected graphical models, called Restricted Boltzmann Machines (RBM's), can be used to model tabular data, such as user's ratings of movies, and demonstrates that RBM's can be successfully applied to the Netflix data set.
TL;DR: This research optimize the amount of marketing funds spent on each customer, rather than just making a binary decision on whether to market to him, and takes into account the fact that knowledge of the network is partial, and that gathering that knowledge can itself have a cost.
Q1. What have the authors contributed in "Circle-based recommendation in online social networks" ?
This paper presents an effort to develop circle-based RS. Through experiments on publicly available data, the authors demonstrate that the proposed circle-based recommendation models can better utilize user ’ s social trust information, resulting in increased recommendation accuracy.
Q2. What are the popular evaluation metrics in the literature of recommender systems?
The evaluation metrics the authors use in their experiments are Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), as these are the most popular accuracy measures in the literature of recommender systems.
Q3. What is the purpose of this paper?
In this paper, the authors focus on low-rank matrix factorization models, as they were found to be one of the most accurate single models for collaborative filtering [5,7,8,19,20].
Q4. What is the purpose of the proposed Circle-based Recommendation model?
Their proposed Circle-based Recommendation (CircleCon) models may be viewed as an extension of the SocialMF model [12] to social networks with inferred circles of friends.
Q5. How many people are relevant in the Kids’ TV Shows category?
For instance, recommendations in the Videos & DVDs category are based on only about half of a user’s friends on average, while in the Kids’ TV Shows category only about 11% of friends are relevant on average.
Q6. What is the way to train for the latent features of all items?
In detail, regarding BaseMF, the authors use all ratings from all categories as input to train for the latent features of all items and all users; for SocialMF, the authors use all category ratings and all trust links as input to train for the latent features of all items and all users.
Q7. What is the heuristic for normalizing v and c?
Like before, the authors then also normalize each row of S(c) matrix (across v), as to make the trust values independent of the activity levels of the users in each circle:S(c)∗u,v = S (c) u,v/ ∑ v∈C(c)u S(c)u,v.
Q8. What is the heuristic for dividing v and u?
In other words, given that u trusts v, if v has more ratings in category c1 than in c2, it is more likely that u trusts v because of v’s ratings in c1 than v’s ratings in c2.