Item popularity and recommendation accuracy

By Harald Steck. 2011

334 citations recorded by the source corpus.

Subfields: Information Systems, Management Science and Operations Research, Marketing

How researchers see this paper

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

In Information Systems

In Management Science and Operations Research

In Marketing

Citations in the corpus

Recommendations as Treatments: Debiasing Learning and Evaluation (2016, methodology): “Related to this setting are also alternative approaches to learning with MNAR data (Steck, 2010; 2011; Lim et al., 2015), which aim to avoid the problem by considering performance measures less affected by selection bias under mild assumptions.”
CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering (2012, neutral): “heavily dominate the recommendation performance [8, 26, 27].”
Ranking with non-random missing ratings: influence of popularity and positivity on evaluation metrics (2012, methodology): “In that sense, we follow [2, 12] and provide an experimental study on the Yahoo! dataset.”
Comparing the Predictive Capability of Social and Interest Affinity for Recommendations (2014, background): “, less popular items) [40], or SRs are superior on cold start users [20, 33].”
Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity (2017, neutral): “We also compare the metric popularity-weighted recall (PW Recall) [42] in the supplementary material.”
Extreme Multi-label Loss Functions for Recommendation, Tagging, Ranking & Other Missing Label Applications (2016, methodology): “Recommending rare items: It is important to remove the popularity bias and recommend rare/novel items in many applications [8, 11, 34, 38, 43, 46, 48, 50].”
Recommender Systems (2016, neutral): “As a result, the accuracy of most recommendation algorithms is different on the more popular items versus the items in the long tail [564].”
Understanding User Beliefs About Algorithmic Curation in the Facebook News Feed (2015, background): “In a typical recommender system, item ratings can be susceptible to popularity bias caused by a feedback loop [31].”
Your neighbors affect your ratings: on geographical neighborhood influence to rating prediction (2014, background): “Moreover, some other work has also shown that popularity is helpful in improving the recommendation accuracy [7, 22].”
Causal Intervention for Leveraging Popularity Bias in Recommendation (2021, background): “One line of research [4, 9, 20, 30, 40] studies the phenomenon of popularity bias.”
Disentangling User Interest and Conformity for Recommendation with Causal Embedding (2021, background): “Existing causal solutions for recommender systems formulate the problem as eliminating popularity bias, from the perspective of items [1, 3, 5, 11, 12, 24, 35, 43].”
The Effect of Recommendations on Network Structure (2016, background): “For example, some of the eﬀects we observe are driven by individuals actively and disproportionately following recommendations for popular users, which may indicate a latent preference for popularity [26].”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “, popularity bias [1, 156] and conformity bias [210, 101], can be removed with introducing the interaction between the user and system.”
Evaluation of recommendations: rating-prediction and ranking (2013, background): “The reason for the diﬀerence is that the ratings are missing not at random (MNAR) in the data sets typically collected [14, 13, 22, 23, 17].”