=Paper=
{{Paper
|id=Vol-3333/paper7
|storemode=property
|title=Mitigation of Popularity Bias in Recommendation Systems
|pdfUrl=https://ceur-ws.org/Vol-3333/Paper7.pdf
|volume=Vol-3333
|authors=Sabrina Karboua,Fouzi Harrag,Farid Meziane,Amal Boutadjine
|dblpUrl=https://dblp.org/rec/conf/tacc/KarbouaHMB22
}}
==Mitigation of Popularity Bias in Recommendation Systems ==
https://ceur-ws.org/Vol-3333/Paper7.pdf
Mitigation of Popularity Bias in Recommendation
Systems
Sabrina. Karboua1,3,* , Fouzi. Harrag1,3 , Farid. Meziane2 and Amal. Boutadjine1,3
1
Departement of Computer Science, College of Sciences, Ferhat ABBAS Setif 1 University, 19000 Setif, Algeria
2
Data Science Research Centre, University of Derby Markeaton Street, Derby DE22 3AW, UK
3
Mechatronics Laboratory, Optics and Precision Mechanics Institute, Ferhat ABBAS University Setif 1, 19000 Setif,
Algeria
Abstract
In response to the quantity of information available on the Internet, many online service providers are
attempting to customize their services and make content access more simple via recommender systems
(RSs) to support users in discovering the products they are most likely interested in. However, these
recommendation systems are prone to popularity bias, which is a tendency to promote popular items
even if they do not satisfy a user’s preferences and then provide customers with recommendations of
poor quality. Such a bias has a negative influence on both users and item providers. It is then essential
to mitigate such bias in order to guarantee that less popular but pertinent items show up on the user’s
recommendation list. In this work, we conduct an empirical analysis of different mitigation techniques
for popularity bias to provide an overview of the present state of the art of popularity bias and raise the
fairness issue in RSs.
Keywords
Popularity bias, Recommender System, Fairness, Mitigation
1. Introduction
Recommendation systems (RSs) have been enormously effective in solving the issue of in-
formation overload, in which users struggle to discover information they are interested in.
We encounter RSs, for example, on Netflix to recommend movies, on Spotify for music rec-
ommendations, on online educational websites to recommend courses like Coursera, when
we get purchase recommendations on e-commerce websites like Amazon, and when we are
advised of new connections on social networking platforms like Facebook. A recommender
system’s performance is often assessed in terms of multiple criteria like accuracy, diversity,
novelty, and fairness. Fairness in RSs is a notion that has lately gained a lot of interest because
developing biased recommendation systems inhibits customers from discovering items that are
not extremely popular yet are good fits for them. Popularity bias is one factor that contributes
to unfairness in RSs as it prevents diverse items from having an equal opportunity of recom-
mendation and exposure. This is a phenomenon in which the most popular items get more
Tunisian Algerian Conference on Applied Computing (TACC 2022), December 13–14, 2022, Constantine, Algeria
$ sabrina.karboua@univ-setif.dz (Sabrina. Karboua); fouzi.harrag@univ-setif.dz (Fouzi. Harrag);
F.Meziane@derby.ac.uk (Farid. Meziane); boutadjine.amal@univ-setif.dz (Amal. Boutadjine)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
and more exposure, while less popular items receive less exposure [1]. Popularity bias occurs
because popular items often have significantly more rating data than less popular ones. This is
because the recommender systems are trained on user preferences, and normally, many users
rate the popular items while the less popular items earn just a few ratings, which implies that
the unpopular items that constitute the so-called long tail of recommendations, do not gain
enough exposure, particularly when they are new to the system [2]. Training RSs models on
biased data promotes the recommendation of popular items more often than less popular ones.
The more rating data the items have, the more they are suggested, and the more the items get
recommended, the more ratings they earn from users, and then "the rich get richer, and the
poor get poorer" [3].
2. Definition of Popularity Bias
Various researchers have studied the idea of popularity bias, which is also known by other
names like Matthew effect [4], long-tail recommendation [5, 6] and aggregate diversity [7].
All of these words refer to the fact that just a few popular items are regularly recommended,
whereas most unpopular items are seldom recommended. The popularity bias of item 𝑖 is
calculated mathematically by dividing the number of users who gave item 𝑖 a rating by the total
number of users [1]. ∑︀
1(𝑖 ∈ 𝑝𝑢 )
𝑃 𝑂𝑃 (𝑖) = 𝑢∈𝑈 ,
|𝑈 |
where 𝑈 represents the list of users and 𝑝𝑢 represents the list of items rated by user 𝑢.
3. Empirical Examples of Popularity Bias and Its Impacts in RSs
Popularity bias has a negative influence not only on the consumers of a recommender system,
but also on the providers, and the system itself. Bias toward popular items may influence
consumption of less popular ones, hinders them from being popular in the future and then
harm the recommendation fairness. The effects of this bias can be better understood through
real-world examples. According to Abdollahpouri et al. [3], popularity bias homogenizes the
market by allowing only a few item producers to dominate it, resulting in fewer chances for
innovation and originality.
Boratto et al. [8] state that in the educational field, an online educational platform recommen-
dation may exhibit undesired bias and subsequent educational amplifications. They demonstrate
that a few popular courses evaluated by a large number of learners might cause the platform to
suffer from popularity bias, preventing new courses from appearing at the top of the suggested
list. As a result, the platform may be controlled by a few well-known courses and consequently
few teachers.
In the music and movie domains, the analysis by [3, 9, 10] reveals that most of items in the
long-tail category do not receive enough exposure and attention, whereas few popular items
are recommended regularly. They highlight also that majority of consumers that have little
interest in popular songs/ movies, would be disadvantaged by the recommendation algorithm
since it tends to recommend popular items, and this leads to an under-recommendation of
unpopular items. Consequently, users that are interested in unpopular songs/ movie will get
lower recommendation than those interested in popular music/ movie.
The findings of [11, 12] in the book domain show that the most frequently used algorithms
are unable to pique users’ interest in niche books and instead promote largely popular books,
and users with niche preferences get much poorer quality recommendation than users with
mainstream tastes.
The research [13] investigates the presence of popularity bias in the online dating websites
and its implications for users’ chances of meeting dating partners. They find that even if the
recommendation algorithm recommends popular users more often, popular users are likely
to accept invitations and messages from those other non-popular users, leading to inferior
matching results.
Gharahighehi al.[14] state that it is quite likely that RSs promote the popularity bias by
recommending only very popular articles, ignoring articles by less popular authors whether
their writings are important to a certain set of readers. This unfair recommendation might
have detrimental effects for these journalists, as they may eventually lose faith in the platfrom,
affecting other parties as well as the whole system.
4. Mitigation Techniques
Most popularity bias mitigation algorithms are categorized into two types: in-processing
algorithms and post-processing algorithms.
4.1. In-processing Techniques
These approaches include altering the recommender system algorithm during training or
introducing new RSs algorithms to incorporate fairness into the model.
1- Causal Graph. A causal graph is a directed acyclic graph, in which each node represents
a variable and each edge represents a causal relationship between two nodes. Zhang et al. [15]
demonstrate that between the exposed items and the observed interactions, item popularity
functions as a confounder, resulting in the negative effect of bias amplification. They use the
causal graph to analyze how item popularity influences the recommendation process.
The causal graph of traditional recommender methods only considers that the interaction
probability (𝐶) of an exposed item (𝐼) that is consumed by user 𝑈 is determined by the match
between user interest and item property (𝑈, 𝐼 → 𝐶). Zhang et al. [15] enrich the graph
by adding the item popularity represented as node Z, which considers that the interaction
probability is based on the user, the exposed item, and the popularity of item (𝑈, 𝐼, 𝐸 → 𝐶).
Popularity Bias
Mitigation
techniques
In-processing Post-processing
Regularization Optimisation
Persoilized
Causal graph
diversification
Variational auto Popularity
encoder Compensation
Adversarial Calibrated
training popularity
Knowledge Graph
Adaptive Boosting
Figure 1: Classification of popularity bias mitigation techniques
Then, they conduct a deconfounded training with do-calculus and back-door criteria to
eliminate the negative influence of the confounder and intervened the popularity bias during
the recommendation inference that provides top-K recommendation list via causal intervention.
Figure 2: proposed causal graph [15]
To overcome popularity bias, Wei et al. [16] disentangle the effects of item popularity and user
interest from causal inference. They first create a causal graph to represent the key cause-effect
relationships in the recommendation model, and assume that the probability of an interaction
is influenced by the user-item matching, user conformity and item popularity. Then, they
propose a model-agnostic counterfactual reasoning (MACR) framework for training the causal
graph-based recommender model and performe counterfactual inference in the recommendation
inference step to reduce popularity bias.
Figure 3: proposed causal graph [16]
Another study similar to [16] is produced by Zheng et al. [17]. They make the assumption
that each click is the result of union of two separate causes: item’s popularity and user’s interest.
Then, they employ different embeddings for the user’s interest and item’s popularity, in order
to have two embeddings for each user or item. After that, they train the model under the
framework of multi-task learning using cause-specific data to constrain each embedding to
represent only one cause and then achieve disentanglement between popularity embedding
and interest embedding. Furthermore, direct disentanglement supervision is used to achieve
greater independence across embeddings of various causes.
Figure 4: proposed causal graph by [17]
Wang et al. [18] present a novel framework DecRS that explicitly incorporates causal effect
of user representation on prediction score and used an approximation operator for backdoor
adjustment to eliminate the misleading correlation induced by the confounder, and then present a
user-specific inference technique for dynamically regulating the impact of backdoor adjustment
based on user state.
He et al. [19] present a novel framework named Mitigating Popularity Prejudice in Recom-
mendation through Counterfactual Inference (MPCI) to eliminate popularity bias from both the
data and model perspectives. MPCI used click data to capture user preference representations
and then extracted biased data to learn popularity bias representations to estimate how popu-
larity bias affects the prediction score in a causal graph, which may then be used to mitigate
its detrimental effect by counterfactual inference. A collection of both positive and negative
samples are included in each representation in order to measure the popularity bias prediction
score and the user preference prediction score using a fusion function. The two scores and the
expectation constant are then combined, and used as the counterfactual inference’s input to
finally predict the user’s prediction score for each item.
Zhao et al. [19] state that not all popularity bias is harmful, because some items are more
popular because they have intrinsically better properties, and removing the popularity bias
completely would deteriorate the model performance. They argue that popularity bias is affected
by two factors: static item quality and the dynamic conformity effect (which refers to user
who follows community standards while diverging from his personal preferences). Therefore,
it is critical to distinguish between the desirable popularity bias induced by item quality and
conformity that leads to bad popularity bias.
Figure 5: proposed causal graph by [19]
To achieve this goal, they propose a novel Time-aware DisEntangled framework (TIDE) using
causal graph to model that a click is generated by three component: conformity effect (𝐶),
item’s quality (𝑄) and item-user matching score(𝑀 ) returned by the recommendation model.
Then, they apply a causal intervention during the inference stage on the conformity module to
help the prediction avoids the undesirable conformity impact and benefits from the item quality
and interest matching.
2- Variational Auto Encoder. VAEs are Multi Layer Perceptrons (MLP)-based generative
models that have recently been presented as a strong method for building Collaborative Filtering
(CF) recommenders and minimizing bias.
To reduce popularity bias and boosting diversity in results, Borges et al. [20] propose to
adapt the VAE by adding a penalty constraint to the reconstruction error (decoder) to boost the
visibility of unpopular items as follow:
𝑁
∑︁
𝑙𝑜𝑔 𝑝(𝑥𝑢 |𝑧𝑢 ) = 𝑥𝑢𝑖 𝑙𝑜𝑔𝜋𝑖 (𝑧𝑢 ).𝜆,
𝑖=0
The penalty term 𝜆 has the effect of lowering the score of the most popular of all items by
multiplying it by 0, while keeping the niche items at their initial score multiplied by 1, and it is
defined as follow:
𝑤(𝑥𝑖 ) − min(𝑤(𝑥))
𝜆=1− ,
max(𝑤(𝑥)) − min(𝑤(𝑥))
where 𝑤(𝑥) returns numbers of interactions for item 𝑥.
3- Regularization. It has been used in matrix factorisation algorithms to control overfitting
by limiting the size of the latent components.
Kiswanto et al. [21] propose a fairness-aware regularization learning-to-rank method to
make the weight of unpopular items higher without affecting the recommender system ranking
performance by recommending a balanced mix of popular and unpopular items to users.
Abdollahpouri et al. [22] investigate how regularization may be used to mitigate the recom-
mender system’s popularity bias. They start with an optimization goal of the form:
min 𝑎𝑐𝑐(𝑃, 𝑄) + 𝜆 𝑟𝑒𝑔(𝑃, 𝑄),
𝑃,𝑄
where 𝑎𝑐𝑐 represents the accuracy target, 𝑟𝑒𝑔 is the regularization term, in which the 𝐿𝑎𝑝𝐷𝑄
regularizer was used, and 𝜆 is a coefficient for managing the regularizer effect. The 𝐿𝑎𝑝𝐷𝑄
regularizer has the form 𝑡𝑟(𝑄𝑇 𝐿𝐷 𝑄), where 𝑡𝑟 is the trace of the matrix D, 𝐿𝐷 is the Laplacian
matrix of D. 𝐷𝑖,𝑗 = 1 if item 𝑖 and 𝑗 are from the same set (popular or unpopular items), and 0
if items 𝑖 and 𝑗are from different set, and 𝑄 is the item latent representation matrix.
Zhu et al. [23] calculate the correlation between the predicted preference score for a positive
user-item and the popularity of matched items using the square of the Pearson regularizer and
then, reduce the bias by reducing this regularization term coupled with the recommendation
error using the following form:
ˆ + , 𝑝𝑜𝑝(𝐼))2 ,
min 𝐿𝑅𝑒𝑐 + 𝜆 𝑃 𝑃 𝐶(𝑅
𝑃,𝑄
where 𝐿𝑅𝑒𝑐 represents the loss of recommendation models, 𝜆 is the trade-off weight, and
𝑃 𝑃 𝐶(.) is the Pearson correlation coefficient between expected scores and items popularity. 𝑅
ˆ
is the predicted user-item preference matrix, and 𝑃 𝑂𝑃 (.) is the item popularity.
4- Adversarial Training. Krishnan et al.[24] propose an adversarial training technique to
mitigate the bias. The adversary network 𝐷 learns in the feedback data the implicit relationship
structure of items, and correlate niche item recommendation of the base recommender 𝐺
with popular items in the user’s history, while the base recommender model 𝐷 is concurrently
trained with the adversary network to replicate these associations while avoiding the adversarial
penalty until mutual convergence. More specifically, The adversary D is taught to differentiate
synthetic pairs of popular and unpopular items selected from 𝐺 and real pairings of popular
and unpopular items obtained from the global co-occurrence of matrix 𝑋. When the synthetic
and real niche-popular pairings match with the association structure acquired by D, the model
converges.
5- Knowledge Graph. Based on the essential assumption that a user often has several
preferences prompting him to consume diverse items, Wei et al. [25] suggest a framework to
mitigate popularity bias from the users’ perspective using knowledge graph, which profiles
user-item connections throughout the knowledge graph using fine-grained preferences, and
then eliminate a proportion of popularity preference for distinct users. The framework seeks
to apply Knowledge Graph integrated with popularity nodes to decrease popularity bias by
determining the fine-grained preferences of users. It initially builds a heterogeneous network
by combining Knowledge Graph, preference graph, and popularity nodes. The embeddings
of item, user, preference and the mutual attention parameters were then learned by applying
a heterogeneous graph transformer to the heterogeneous graph while matching fine-grained
preferences with the relations in Knowledge Graph. Finally, popularity preference is removed
adaptively based on the user’s interest in popular items to reduce the bias.
6- Adaptive Boosting. Inspired by the fair boosting technique on classification. Gangwar et
al. [26] provide an algorithm named "FairBoost" that minimizes the popularity bias existing
in the data while preserving accuracy within reasonable bounds, by increasing the weights of
the unpopular items, which are typically under-represented in the data and then, maintain a
balance between popular and unpopular items.
4.2. Post-Processing Techniques
This kind of techniques may be applied to any recommender system’s output by reordering
the original recommended list based on some constraints.
1- Knapsack Optimization model. Seymen et al.[27] propose a re-ranking optimization
model to find the best system solution given diverse constraints to deal with various different
problems like popularity bias, diversity and provider fairness. They start by defining a baseline
model to increase the overall recommended items’ average predicted ratings, with the restriction
that each user gets K recommendation.
1 ∑︁ ∑︁
𝑟𝑖𝑢 𝑥𝑖𝑢 ,
𝐾|𝑈 |
𝑖∈𝐼 𝑢∈𝑈
where I is the set of items 𝑎𝑛𝑑U is the set of users, K is the number of items to be recom-
mended to each user, 𝑟𝑖𝑢 represents the predicted rating for user u ∈ U and item i ∈ I . xij is a
binary value (an item is either recommended or not) that specifies items that are recommended,
where xij = 1 if item i is recommended to user u and 0 otherwise.
Then, They extend the base model by adding a knapsack constraint (Pop-Opt) to leverage the
popularity of all recommended items as follows.
∑︁ ∑︁
𝑥𝑖𝑢 𝜔𝑖 ≤ 𝛼,
𝑖∈𝐼 𝑢∈𝑈
where 𝛼 represents the maximum bound on the overall popularity of the recommended items
and 𝜔𝑖 calculates the item’s popularity i by dividing the number of ratings received by item i
by the sum of all the ratings for all other items in the system.
2- Personilazed diversification approach. To decrease the effect of popularity bias, a
new post-processing method is proposed by Abdollahpouri et al. [28] by reordering the initial
recommendation list provided by the recommender algorithm. They improve a diversification
technique’ aim is to achieve the required compromise between accuracy and long-tail coverage
(improve the representation of underrepresented items). Their strategy is based on an algorithm
named the eXplicit Query Aspect Diversification (xQuAD), which is developed to diversify
query results so it addresses a wide range of query components. They apply the following
criterion on the final recommendation list to maintain a balance between ratio of popular items
and niche items as follow:
𝑃 (𝑣|𝑢) + 𝜆 𝑃 (𝑣, 𝑆 ′ |𝑢),
𝑃 (𝑣|𝑢) indicates the probability that a user 𝑢 ∈ 𝑈 (list of users) is interested in item 𝑣 ∈ 𝑉
(list of items), and 𝑃 (𝑣, 𝑆 ′ |𝑘) reflects the probability that user 𝑢 will be interested in item 𝑣 and
that 𝑣 is not already in S (new re-ordered list). The first term emphasizes diversity between
popular and unpopular items, whereas the second term encourages scoring accuracy. In general,
𝜆 parameter affects how highly the regulating of popularity bias is weighted. The item with the
highest score is included in the final list 𝑆, then repeated the procedure until 𝑆 achieves required
length. In order to produce more diversified recommendation that includes both popular Γ and
unpopular Γ’ items, the marginal probability 𝑃 (𝑣, 𝑆 ′ |𝑢) is computed as:
∑︁ ∏︁
𝑃 (𝑣, 𝑆 ′ |𝑢) = 𝑃 (𝑑|𝑢)𝑃 (𝑣|𝑑) (1 − 𝑃 (𝑖|𝑑𝑆),
𝑑∈Γ,Γ′ 𝑖∈𝑆
where 𝑃 (𝑑|𝑢) is an indicator of user preference across distinct item groups, 𝑃 (𝑑|𝑣) is equal
to 1 if item 𝑖 in the original recommended list 𝑆 includes category 𝑑 and 0 otherwise.
3- Calibrated popularity. A distributional discrepancies in the groups (short-head, medium,
tail) to which items belong between the user’s profile and its recommended list is measured.
The principle of calibrated popularity (CP) is that for example, if a user likes 10% popular
items, 30% items of medium popularity, and 40% unpopular items, the recommended list should
comprise 10% popular items, 30% items of medium popularity, and 40% niche items [29]. The
Calibrated Popularity method generates a final recommendation list 𝐿𝑢 for each user 𝑢 from an
initial recommended list 𝑆 created by a base recommender. A weighted sum of relevance and
calibration is used and maximized as follow
𝐹𝑢 = 𝑎𝑟𝑔 𝑚𝑎𝑥(1 − 𝜆).𝑅𝑒𝑙(𝐿𝑢 ) − 𝜆.ℑ(𝑃, 𝑄(𝐿𝑢 )),
where 𝜆 is the weight regulating popularity calibration vs the relevance, 𝑅𝑒𝑙(𝐿𝑢 ) is the total
of the predicted scores for items in 𝐿𝑢 . ℑ represents the jenson-shanon divergence between
the recommendation profile and recommendation list items.
4- Popularity Compensation. Another research [23] introduces another re-ranking strat-
egy that alters the predicted user-item preference matrix by compensating low-popularity
items so that they have greater preference scores and therefore, they are ranked higher. This
compensation is based on three key principles:
- Should be dependent on item popularity, with less popular items receiving higher compen-
sation.
- Compensation should be also dependent on user preferences; items that have higher
possibility of being preferred by a user should be rewarded more. The algorithm therefore
assures that items that are not liked by a user and has a low popularity will not be recommended
by mistake.
- Compensation should be based on each user’s value scale: item candidates for a user with a
higher value scale should be compensated more. This ensures that consumers with high value
scales of estimated scores receive adequate compensation for items, ensuring that the algorithm
is useful to all users.
For one item 𝑖 given user 𝑢, the popularity compensation score is calculated using the
following equation:
1 ˆ 𝑢,𝑖 .𝛽 + 1 − 𝛽),
𝐶𝑢,𝑖 = .(𝑅
𝑝𝑜𝑝(𝑖)
where 𝑅 ˆ 𝑢,𝑖 is the predicted preference scores from user 𝑢 to items produced by the algorithm.
1/𝑝𝑜𝑝(𝑖) used to achieve the first condition. 𝑅𝑢,𝑖 .𝛽 + 1 − 1 to achieve the second condition. 𝛽 ∈
[0, 1] is a trade-off weight used to adjust the predicted preference score ratio in the compensation.
Condition 3 is calculated using the following equation:
𝑅ˆ* 𝑢,𝑖 = 𝑅
ˆ 𝑢,𝑖 .𝛼 + 𝐶𝑢,𝑖 .𝑛𝑢 /𝑚𝑢 ,
*
where 𝑅ˆ 𝑢,𝑖 is the new preference score from 𝑢 to 𝑖, 𝛼 represents the algorithm’s trade-off
weight, and 𝑛𝑢 /𝑚𝑢 used to normalize the compensation scores (𝑛𝑢 represents predicted scores
norm for user 𝑢 and 𝑚𝑢 is the compensation scores norm of 𝑢 excepting those for items in the
interacted item set in the training data).
5. Conclusion
In this paper, we explained the issue of popularity bias in Recommenders System (RSs), then we
systematically provided a mitigation techniques classification into two approaches in-processing
(model based) and post-processing (re- ranking). The first approach is based on improving
current algorithms by adding a constraint into the objective function or propose new algorithms.
In the second approach, the original recommended list is re-ordered based on some constraints
to mitigate the popularity bias.
References
[1] H. Abdollahpouri, Popularity bias in recommendation: a multi-stakeholder perspective,
Ph.D. thesis, University of Colorado at Boulder, 2020.
[2] E. Yalcin, A. Bilge, Investigating and counteracting popularity bias in group recommenda-
tions, Information Processing & Management 58 (2021) 102608.
[3] H. Abdollahpouri, M. Mansoury, R. Burke, B. Mobasher, The unfairness of popularity bias
in recommendation, arXiv preprint arXiv:1907.13286 (2019).
[4] J. Möller, D. Trilling, N. Helberger, B. van Es, Do not blame it on the algorithm: an
empirical assessment of multiple recommender systems and their impact on content
diversity, Information, Communication & Society 21 (2018) 959–977.
[5] H. Abdollahpouri, R. Burke, B. Mobasher, Controlling popularity bias in learning-to-rank
recommendation, in: Proceedings of the eleventh ACM conference on recommender
systems, 2017, pp. 42–46.
[6] H. Yin, B. Cui, J. Li, J. Yao, C. Chen, Challenging the long tail recommendation, arXiv
preprint arXiv:1205.6700 (2012).
[7] G. Adomavicius, Y. Kwon, Improving aggregate recommendation diversity using ranking-
based techniques, IEEE Transactions on Knowledge and Data Engineering 24 (2011)
896–911.
[8] L. Boratto, G. Fenu, M. Marras, The effect of algorithmic bias on recommender systems for
massive open online courses, in: European Conference on Information Retrieval, Springer,
2019, pp. 457–472.
[9] D. Kowald, M. Schedl, E. Lex, The unfairness of popularity bias in music recommendation:
A reproducibility study, in: European conference on information retrieval, Springer, 2020,
pp. 35–42.
[10] C. Bauer, M. Schedl, Global and country-specific mainstreaminess measures: Definitions,
analysis, and usage for improving personalized music recommendation systems, PloS one
14 (2019) e0217389.
[11] M. Naghiaei, H. A. Rahmani, M. Dehghan, The unfairness of popularity bias in book
recommendation, arXiv preprint arXiv:2202.13446 (2022).
[12] M. Naghiaei, H. A. Rahmani, M. Dehghan, The unfairness of popularity bias in book
recommendation, arXiv preprint arXiv:2202.13446 (2022).
[13] M. Celdir, S.-H. Cho, E. H. Hwang, Popularity bias in online dating platforms: Theory and
empirical evidence, Available at SSRN 4053204 (2022).
[14] A. Gharahighehi, C. Vens, K. Pliakos, Fair multi-stakeholder news recommender system
with hypergraph ranking, Information Processing & Management 58 (2021) 102663.
[15] Y. Zhang, F. Feng, X. He, T. Wei, C. Song, G. Ling, Y. Zhang, Causal intervention for
leveraging popularity bias in recommendation, in: Proceedings of the 44th International
ACM SIGIR Conference on Research and Development in Information Retrieval, 2021, pp.
11–20.
[16] T. Wei, F. Feng, J. Chen, Z. Wu, J. Yi, X. He, Model-agnostic counterfactual reasoning for
eliminating popularity bias in recommender system, in: Proceedings of the 27th ACM
SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 1791–1800.
[17] Y. Zheng, C. Gao, X. Li, X. He, Y. Li, D. Jin, Disentangling user interest and conformity for
recommendation with causal embedding, in: Proceedings of the Web Conference 2021,
2021, pp. 2980–2991.
[18] W. Wang, F. Feng, X. He, X. Wang, T.-S. Chua, Deconfounded recommendation for
alleviating bias amplification, in: Proceedings of the 27th ACM SIGKDD Conference on
Knowledge Discovery & Data Mining, 2021, pp. 1717–1725.
[19] M. He, C. Li, X. Hu, X. Chen, J. Wang, Mitigating popularity bias in recommendation via
counterfactual inference, in: International Conference on Database Systems for Advanced
Applications, Springer, 2022, pp. 377–388.
[20] R. Borges, K. Stefanidis, On mitigating popularity bias in recommendations via variational
autoencoders, in: Proceedings of the 36th Annual ACM Symposium on Applied Computing,
2021, pp. 1383–1389.
[21] D. Kiswanto, D. Nurjanah, R. Rismala, Fairness aware regularization on a learning-to-rank
recommender system for controlling popularity bias in e-commerce domain, in: 2018
International Conference on Information Technology Systems and Innovation (ICITSI),
IEEE, 2018, pp. 16–21.
[22] H. Abdollahpouri, R. Burke, B. Mobasher, Controlling popularity bias in learning-to-rank
recommendation, in: Proceedings of the eleventh ACM conference on recommender
systems, 2017, pp. 42–46.
[23] Z. Zhu, Y. He, X. Zhao, Y. Zhang, J. Wang, J. Caverlee, Popularity-opportunity bias in
collaborative filtering, in: Proceedings of the 14th ACM International Conference on Web
Search and Data Mining, 2021, pp. 85–93.
[24] A. Krishnan, A. Sharma, A. Sankar, H. Sundaram, An adversarial approach to improve
long-tail performance in neural collaborative filtering, in: Proceedings of the 27th ACM
International Conference on information and knowledge management, 2018, pp. 1491–
1494.
[25] F. Wei, S. Chen, J. Jin, S. Zhang, H. Zhou, Y. Wu, Adaptive alleviation for popularity bias
in recommender systems with knowledge graph, Security and Communication Networks
2022 (2022).
[26] A. Gangwar, S. Jain, An adaptive boosting technique to mitigate popularity bias in
recommender system, arXiv preprint arXiv:2109.05677 (2021).
[27] S. Seymen, H. Abdollahpouri, E. C. Malthouse, A unified optimization toolbox for solving
popularity bias, fairness, and diversity in recommender systems., in: MORS@ RecSys,
2021.
[28] H. Abdollahpouri, R. Burke, B. Mobasher, Managing popularity bias in recommender
systems with personalized re-ranking, in: The thirty-second international flairs conference,
2019.
[29] H. Abdollahpouri, M. Mansoury, R. Burke, B. Mobasher, E. Malthouse, User-centered
evaluation of popularity bias in recommender systems, in: Proceedings of the 29th ACM
Conference on User Modeling, Adaptation and Personalization, 2021, pp. 119–129.