TrustWalker: a random walk model for combining trust-based and item-based recommendation

By Mohsen Jamali, Martin Ester. 2009

925 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

How researchers see this paper

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

In Artificial Intelligence

In Computer Networks and Communications

In Information Systems

Citations in the corpus

Collaborative Topic Regression with Social Matrix Factorization for Recommendation Systems (2012, methodology): “To overcome the major weaknesses of CF-based recommendation systems, many models have been proposed to explore additional information, such as item’s content information (Basilico & Hofmann, 2004; Wang & Blei, 2011) and user’s social network (Jamali & Ester, 2009; Ma et al., 2008).”
A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “In this process, multiple types of side information have been explored, such as item attributes [7], [8], item reviews [9], [10], and users’ social networks [11], [12].”
Temporal recommendation on graphs via long- and short-term preference fusion (2010, methodology): “erences on items, [3, 15, 12, 7] proposed their personalized random walk models respectively to make recommendation in different domains.”
Foliar heavy metal uptake, toxicity and detoxification in plants: A comparison of foliar and root metal uptake. (2017, neutral): “Explicit trust denotes the trust values explicitly indicated by their users [30] [9] [16].”
Exploiting geographical influence for collaborative point-of-interest recommendation (2011, background): “Recent studies have argued that social friends tend to share common interests and thus can be used in the process of collaborative filtering for making recommendations [11, 12, 2, 13, 24].”
Ieee Transactions on Knowledge and Data Engineering, Manuscropt Id 1 Social Recommendation with Cross-domain Transferable Knowledge (positive): “TrustWalker [10] defined and measured the confidence of a recommendation with .2×10 −6 7.8×10 −6 user label 5,715 7,604,679 - - 9.3×10 −4 - a random walk model to combine the trust-based and CF approaches.”
A new user similarity model to improve the accuracy of collaborative filtering (2014, background): “Jamali and Ester [15] introduced a similarity measure based on the sigmoid function.”
Neural Graph Collaborative Filtering (2019, background): “Another line of research [3, 15, 19, 29, 42] exploits the user-item interaction graph to infer user preference.”
Adversarial Web Search (2011, methodology): “One method of this type is the TrustWalker method by Jamali and Ester [108] in which reviews in a collaborative recommendation platform are scored by trust.”
Exploring social influence for recommendation: a generative model approach (2012, methodology): “, friends share some common interests) and propose to exploit the correlation for item recommendations [12, 16, 17, 18, 19, 6].”
mTrust: discerning multi-faceted trust in a connected world (2012, background): “Assuming that users are likely to have similar preferences with their trust networks, trust networks are widely exploited in collaborative filtering [8, 1], intelligent recommender systems [17, 5], review quality prediction [15] and viral marketing [22] to improve the accuracy.”
Social Recommendation with Strong and Weak Ties (2016, methodology): “Jamali et al. [25] reported that in the Epinions dataset, about 50% of the users are deemed cold-start (who rated less than ﬁve items).”
Location recommendation for location-based social networks (2010, background): “(c) 2010ACM ISBN 978-1-4503-0428-3/10/11...$10.00. networking services allow users to connect with friends, explore places (e.g., restaurants, stores, cinema theaters, etc), share their locations, and upload photos, video, and blogs.”
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems (2019, background): “ advantage of social networks to alleviate the data sparsity problem for item recommendation. „en many following studies begin to model social e‡ects in recommender systems from various perspectives. [5, 12, 21] propose trust propagation methods by leveraging rating of friends to deduce rating of ta”
Personalized Recommendation Combining User Interest and Social Circle (2014, neutral): “Many social network based models [3], [13]–[19], [33]– [37] have been proposed to improve the performance of the RS. Recently, Yang et al. [1] propose to use the concept of 'inferred trust circle' based on the domain-obvious circles of friends on social networks to recommend user favorite items.”
Recommender Systems (2012, background): “Trust can be used instead of user similarity [239], in combination with collaborative filtering to help deal with data sparsity and the cold start problem [240, 241, 242], or it can help to further filter recommendations by prioritizing those approved by trusted sources (see [243] for a review).”
Comparative Deep Learning of Hybrid Representations for Image Recommendations (2016, background): “With the development of social networks, recent research starts to leverage social data to improve the performance of recommendations [8, 10].”
Inferring Latent Network from Cascade Data for Dynamic Social Recommendation (2016, background): “Early research [11] [21] searches the trust network to determine the recommended items.”
A matrix factorization technique with trust propagation for recommendation in social networks (2010, methodology): “In order to consider enough ratings without suffering from noisy data, [5] proposes a random walk method (TrustWalker) combines trust-based and item-based recommendation.”