Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques

By Gediminas Adomavicius, YoungOk Kwon. 2012

737 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Information Systems, Management Science and Operations Research

How researchers see this paper

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

In Electrical and Electronic Engineering

In Information Systems

In Management Science and Operations Research

Citations in the corpus

User-oriented Fairness in Recommendation (2021, background): “Such researches mainly solve this problem by increasing the number of recommended unpopular items (long-tail items) or otherwise the overall catalog coverage [2, 3, 5, 21].”
Multistakeholder recommendation: Survey and research directions (2020, methodology): “In the first simulation experiment, we adopted the greedy item re-ranking scheme from [5] to maximize the profit of the top-10 recommended items.”
Evaluation of session-based recommendation algorithms (2018, background): “This measure represents a form of catalog coverage, which is sometimes referred to as aggregate diversity (Adomavicius and Kwon 2012).”
Hybrid recommender systems: A systematic literature review (2017, background): “. As a characteristic it reﬂects the usefulness of the system. The higher the coverage (more items predicted and recommended) the more useful the recommender system for the users. In other works like [37] it is only considered as a metric with which the authors evaluate diversity, another recommenda”
A survey on sentiment analysis methods, applications, and challenges (2022, methodology): “The feature is ranked using several statistical metrics, and then the features with the highest rankings are chosen (Adomavicius and Kwon 2011).”
Controllable Multi-Interest Framework for Recommendation (2020, background): “Many studies focus on improving aggregated diversity of recommendation systems [1, 2, 40, 43].”
Diversity, Serendipity, Novelty, and Coverage (2016, methodology): “…means exposing the users to a wider range of recommended items, which may both increase the users' satisfaction with the system (e.g., by recommending items the user would not otherwise discover) [Adomavicius and Kwon 2012] and benefit business owners (increasing the sales of the long-tail items).”
Diversity in Big Data: A Review (2017, neutral): “37 Other possible examples include matchmaking, where we may want to diversify the proposed dating partners across users, and graduate school admissions, where we may opt to diversify across schools to avoid having the exact same admissions lists.”
A probabilistic model to resolve diversity–accuracy challenge of recommendation systems (2015, background): “A practical recommender system should not only have a good accuracy but also provide proper novelty and diversity of items for the users [1,39].”
Schema-summarization in linked-data-based feature selection for recommender systems (2017, background): “To evaluate aggregate diversity, we consider catalog coverage (the percentage of items in the catalog recommended at least once) and aggregate entropy [1].”
Sound and Music Recommendation with Knowledge Graphs (2016, methodology): “In our work, we adopt the diversity-in-top-N metric presented in Adomavicius and Kwon [2012] that 21:11 measures the distinct items recommended across all users.”
A Survey on Bayesian Deep Learning (2016, neutral): “Take recommender systems [1, 70, 71, 92, 121] as another example.”
Managing Popularity Bias in Recommender Systems with Personalized Re-ranking (2019, background): “Recommending serendipitous items from the long tail is generally considered to be a key function of recommendation (Anderson 2006), as these are items that users are less likely to know about.”
Controlling Polarization in Personalization: An Algorithmic Framework (2019, background): “Another approach would be to manipulate the user ratings (e.g., by adding noise or a regularizer to the recommender algorithm) in order to have only approximate preferences; this has been shown to help reduce polarization [4, 5, 38].”
Diversity in recommender systems - A survey (2017, background): “Adomavicius and Kwon [51] introduced a series of item ranking techniques that can Advantages and disadvantages of the most relevant diversiﬁcation algorithms.”