Search

User modeling is a key topic in many applications, mainly social networks and information retrieval systems. To assess the effectiveness of a user modeling approach, its capability to classify personal characteristics (e.g., the gender, age, or consumption grade of the users) is evaluated. Due to the fact that some of the attributes to predict are multiclass (e.g., age usually encompasses multiple ranges), assessing fairness in user modeling becomes a challenge since most of the related metrics work with binary attributes. As a workaround, the original multiclass attributes are usually binarized to meet standard fairness metrics definitions where both the target class and sensitive attribute (such as gender or age) are binary. However, this alters the original conditions, and fairness is evaluated on classes that differ from those used in the classification. In this article, we extend the definitions of four existing fairness metrics (related to disparate impact and disparate mistreatment) from binary to multiclass scenarios, considering different settings where either the target class or the sensitive attribute includes more than two groups. Our work endeavors to bridge the gap between formal definitions and real use cases in bias detection. The results of the experiments, conducted on four real-world datasets by leveraging two state-of-the-art graph neural network-based models for user modeling, show that the proposed generalization of fairness metrics can lead to a more effective and fine-grained comprehension of disadvantaged sensitive groups and, in some cases, to a better analysis of machine learning models originally deemed to be fair. The source code and the preprocessed datasets are available at the following link: . [ABSTRACT FROM AUTHOR]

Location-Based Social Networks stimulated the rise of services such as Location-based Recommender Systems. These systems suggest to users points of interest (or venues) to visit when they arrive in a specific city or region. These recommendations impact various stakeholders in society, like the users who receive the recommendations and venue owners. Hence, if a recommender generates biased or polarized results, this affects in tangible ways both the experience of the users and the providers' activities. In this paper, we focus on four forms of polarization, namely venue popularity, category popularity, venue exposure, and geographical distance. We characterize them on different families of recommendation algorithms when using a realistic (temporal-aware) offline evaluation methodology while assessing their existence. Besides, we propose two automatic approaches to mitigate those biases. Experimental results on real-world data show that these approaches are able to jointly improve the recommendation effectiveness, while alleviating these multiple polarizations. [ABSTRACT FROM AUTHOR]

Offering timely support to users in eCoaching systems is a key factor to keep them engaged. However, coaches usually follow a lot of users, so it is hard for them to prioritize those with whom they should interact first. Timeliness is especially needed when health implications might be the consequence of a lack of support. In this paper, we focus on this last scenario, by considering an eCoaching platform for runners. Our goal is to provide a coach with a ranked list of users, according to the support they need. Moreover, we want to guarantee a fair exposure in the ranking, to make sure that users of different groups have equal opportunities to get supported. In order to do so, we first model their performance and running behavior and then present a ranking algorithm to recommend users to coaches, according to their performance in the last running session and the quality of the previous ones. We provide measures of fairness that allow us to assess the exposure of users of different groups in the ranking and propose a re-ranking algorithm to guarantee a fair exposure. Experiments on data coming from the previously mentioned platform for runners show the effectiveness of our approach on standard metrics for ranking quality assessment and its capability to provide a fair exposure to users. The source code and the preprocessed datasets are available at: https://github.com/wiguider/Fair-Performance-based-User-Recommendation-in-eCoaching-Systems. [ABSTRACT FROM AUTHOR]

Ranking systems have an unprecedented influence on how and what information people access, and their impact on our society is being analyzed from different perspectives, such as users' discrimination. A notable example is represented by reputation-based ranking systems, a class of systems that rely on users' reputation to generate a non-personalized item-ranking, proved to be biased against certain demographic classes. To safeguard that a given sensitive user's attribute does not systematically affect the reputation of that user, prior work has operationalized a reputation independence constraint on this class of systems. In this paper, we uncover that guaranteeing reputation independence for a single sensitive attribute is not enough. When mitigating biases based on one sensitive attribute (e.g., gender), the final ranking might still be biased against certain demographic groups formed based on another attribute (e.g., age). Hence, we propose a novel approach to introduce reputation independence for multiple sensitive attributes simultaneously. We then analyze the extent to which our approach impacts on discrimination and other important properties of the ranking system, such as its quality and robustness against attacks. Experiments on two real-world datasets show that our approach leads to less biased rankings with respect to multiple users' sensitive attributes, without affecting the system's quality and robustness. [ABSTRACT FROM AUTHOR]

Online education platforms play an increasingly important role in mediating the success of individuals' careers. Therefore, while building overlying content recommendation services, it becomes essential to guarantee that learners are provided with equal recommended learning opportunities, according to the platform principles, context, and pedagogy. Though the importance of ensuring equality of learning opportunities has been well investigated in traditional institutions, how this equality can be operationalized in online learning ecosystems through recommender systems is still under-explored. In this paper, we shape a blueprint of the decisions and processes to be considered in the context of equality of recommended learning opportunities, based on principles that need to be empirically-validated (no evaluation with live learners has been performed). To this end, we first provide a formalization of educational principles that model recommendations' learning properties, and a novel fairness metric that combines them to monitor the equality of recommended learning opportunities among learners. Then, we envision a scenario wherein an educational platform should be arranged in such a way that the generated recommendations meet each principle to a certain degree for all learners, constrained to their individual preferences. Under this view, we explore the learning opportunities provided by recommender systems in a course platform, uncovering systematic inequalities. To reduce this effect, we propose a novel post-processing approach that balances personalization and equality of recommended opportunities. Experiments show that our approach leads to higher equality, with a negligible loss in personalization. This paper provides a theoretical foundation for future studies of learners' preferences and limits concerning the equality of recommended learning opportunities. [ABSTRACT FROM AUTHOR]

The correction notice in the journal "Data Mining & Knowledge Discovery" addresses a missing acknowledgment in an article on bias in location-based recommender systems. The authors failed to reference the project "AmerMad-CM: America in Madrid" in the original article, which was co-financed by the Community of Madrid and the European Social Fund. The correction has been made to the article, and Springer Nature maintains neutrality regarding jurisdictional claims and affiliations. [Extracted from the article]

The spread of online reviews and opinions and its growing influence on people's behavior and decisions boosted the interest to extract meaningful information from this data deluge. Hence, crowdsourced ratings of products and services gained a critical role in business and governments. Current state-of-the-art solutions rank the items with an average of the ratings expressed for an item, with a consequent lack of personalization for the users, and the exposure to attacks and spamming/spurious users. Using these ratings to group users with similar preferences might be useful to present users with items that reflect their preferences and overcome those vulnerabilities. In this article, we propose a new reputation-based ranking system, utilizing multipartite rating subnetworks, which clusters users by their similarities using three measures, two of them based on Kolmogorov complexity. We also study its resistance to bribery and how to design optimal bribing strategies. Our system is novel in that it reflects the diversity of preferences by (possibly) assigning distinct rankings to the same item, for different groups of users. We prove the convergence and efficiency of the system. By testing it on synthetic and real data, we see that it copes better with spamming/spurious users, being more robust to attacks than state-of-the-art approaches. Also, by clustering users, the effect of bribery in the proposed multipartite ranking system is dimmed, comparing to the bipartite case. [ABSTRACT FROM AUTHOR]

Recent observational studies highlight the importance of considering the interactions between users in the group recommendation process, but to date their integration has been marginal. In this article, we propose a collaborative model based on the social interactions that take place in a web-based conversational group recommender system. The collaborative model allows the group recommender to implicitly infer the different roles within the group, namely, collaborative and leader user(s). Moreover, it serves as the basis of several novel collaboration-based consensus strategies that integrate both individual and social interactions in the group recommendation process. A live-user evaluation confirms that our approach accurately identifies the collaborative and leader users in a group and produces more effective recommendations. [ABSTRACT FROM AUTHOR]

Considering the impact of recommendations on item providers is one of the duties of multi-sided recommender systems. Item providers are key stakeholders in online platforms, and their earnings and plans are influenced by the exposure their items receive in recommended lists. Prior work showed that certain minority groups of providers, characterized by a common sensitive attribute (e.g., gender or race), are being disproportionately affected by indirect and unintentional discrimination. Our study in this paper handles a situation where (i) the same provider is associated with multiple items of a list suggested to a user, (ii) an item is created by more than one provider jointly, and (iii) predicted user–item relevance scores are biasedly estimated for items of provider groups. Under this scenario, we assess disparities in relevance, visibility, and exposure, by simulating diverse representations of the minority group in the catalog and the interactions. Based on emerged unfair outcomes, we devise a treatment that combines observation upsampling and loss regularization, while learning user–item relevance scores. Experiments on real-world data demonstrate that our treatment leads to lower disparate relevance. The resulting recommended lists show fairer visibility and exposure, higher minority item coverage, and negligible loss in recommendation utility. [ABSTRACT FROM AUTHOR]

eCoaching platforms have become powerful tools to support users in their day-to-day physical routines. More and more research works show that motivational factors are strictly linked with the user inclination to share her fitness achievements on social media platforms. In this paper, we tackle the problem of analyzing and modeling users' contextual information and real-time training data by exploiting state-of-the-art classification algorithms, to predict if a user will share her current running workout on Facebook. By analyzing user's performance, collected by means of an eCoaching platform for runners, and crossing them with contextual information such as the weather, we are able to predict with a high accuracy if the user will post or not on Facebook. Given the positive impact that social media posts have in these scenarios, understanding what are the conditions that lead a user to post or not, can turn the output of the classification process into actionable knowledge. This knowledge can be exploited inside eCoaching platforms to model user behavior in broader and deeper ways, to develop novel forms of intervention and favor users' motivation on the long term. [ABSTRACT FROM AUTHOR]

Journey planners support users in the organization of their trips, by presenting them results with multimodal solutions. While the benefits for the users are straightforward, other stakeholders (such as transport operators and planners) might benefit from understanding how users behave. In this paper, we analyze and characterize user behavior in journey planners, with the aim of getting insights from different perspectives (namely, trip search and both sorting and selection actions related to trip options). Our results show that, in order to characterize user behavior, multiple perspectives have to be taken into account, and that users speaking different languages behave differently. [ABSTRACT FROM AUTHOR]

Nowadays, we are inundated with data gathered from the users, both in the real- and in the digital-world. Data-driven decision making in critique-based recommenders: from a critique to social media data Journal of Intelligent Information Systems. [Extracted from the article]

An introduction is presented in which the editors discuss various reports within the issue on topics including data mining, big data and information system.

In the last few years, social media systems have experienced a fast growth. The amount of content shared in these systems increases fast, leading users to face the well known “interaction overload” problem, i.e., they are overwhelmed by content, so it becomes difficult to come across interesting items. To overcome this problem, social recommender systems have been recently designed and developed in order to filter content and recommend to users only interesting items. This type of filtering is usually affected by the “over-specialization” problem, which is related to recommendations that are too similar to the items already considered by the users. This paper proposes a friend recommender system that operates in the social bookmarking application domain and is based on behavioral data mining, i.e., on the exploitation of the users activity in a social bookmarking system. Experimental results show how this type of mining is able to produce accurate friend recommendations, allowing users to get to know bookmarked resources that are both novel and serendipitous. Using this approach, the impact of the “interaction overload” and the “over-specialization” problems is strongly reduced. [ABSTRACT FROM AUTHOR]

This article presents a novel approach to monitoring athletes’ behavioral changes to predict a decline in motivation. When the system detects such a decline, it refers the athlete to her coach, along with a concise explanation of the detected behavioral changes. The coach thus has all the information needed for a prompt, targeted intervention. [ABSTRACT FROM AUTHOR]

Nowadays, the use of mobile applications and wearable technologies to support and encourage an active lifestyle has become widespread. Several studies put in evidence that the usage of these kinds of support has to be monitored by high-qualified figures, to favor a safe and a long-term adherence to training routines. In order to investigate the impact of these professionals, this work sets out to provide an overview and an evaluation of an e-coaching ecosystem specifically designed for runners. The platform supports and guides people towards an active lifestyle by stimulating their motivation to exercise through the engagement provided by the interactions between users and human trainers. In this study, we investigate the effectiveness of the support offered by the human trainers and the engagement of the users. The results show that the support of human qualified trainers is crucial. Users tend to be more engaged to train when their trainings are developed and remotely supervised by a human coach. This has resulted in more workout sessions performed with respect to users exercising by following standard or self-made routines without direct professional supervision. Our findings show that e-coaching systems should develop their coaching protocols always taking into account the effectiveness of the support of qualified professionals over completely automated approaches. [ABSTRACT FROM AUTHOR]

Recommender systems suggest items that might be interesting to a user. To achieve this, rating prediction is the main form of information processing that these systems perform. This article tackles the problem of predicting ratings in a group recommender system by analyzing how system accuracy is influenced by the choice of prediction approach and by a solution that employs the predicted values to avoid data sparsity. The results of more than 100 experiments show that by predicting the ratings for individual users instead of predicting them for groups, and by using these predictions in a system's group detection task, accuracy increases and problems caused by data sparsity are reduced. [ABSTRACT FROM PUBLISHER]

Recommender systems usually suggest items by exploiting all the previous interactions of the users with a system (e.g., in order to decide the movies to recommend to a user, all the movies she previously purchased are considered). This canonical approach sometimes could lead to wrong results due to several factors, such as a change in user preferences over time, or the use of her account by third parties. This kind of incoherence in the user profiles defines a lower bound on the error the recommender systems may achieve when they generate suggestions for a user, an aspect known in literature as magic barrier. This paper proposes a novel dynamic coherence-based approach to define the user profile used in the recommendation process. The main aim is to identify and remove, from the previously evaluated items, those not semantically adherent to the others, in order to make a user profile as close as possible to the user's real preferences, solving the aforementioned problems. Moreover, reshaping the user profile in such a way leads to great advantages in terms of computational complexity, since the number of items considered during the recommendation process is highly reduced. The performed experiments show the effectiveness of our approach to remove the incoherent items from a user profile, increasing the recommendation accuracy. [ABSTRACT FROM AUTHOR]

Group recommender systems provide suggestions when more than a person is involved in the recommendation process. A particular context in which group recommendation is useful is when the number of recommendation lists that can be generated is limited (i.e., it is not possible to suggest a list of items to each user). In such a case, grouping users and producing recommendations to groups becomes necessary. None of the approaches in the literature is able to automatically group the users in order to overcome the previously presented limitation. This paper presents a set of group recommender systems that automatically detect groups of users by clustering them, in order to respect a constraint on the maximum number of recommendation lists that can be produced. The proposed systems have been largely evaluated on two real-world datasets and compared with hundreds of experiments and statistical tests, in order to validate the results. Moreover, we introduce a set of best practices that help in the development of group recommender systems in this context. [ABSTRACT FROM AUTHOR]

A recommender system suggests items to users by predicting what might be interesting for them. The prediction task has been highlighted in the literature as the most important one computed by a recommender system. Its role becomes even more central when a system works with groups, since the predictions might be built for each user or for the whole group. This paper presents a deep evaluation of three approaches, used for the prediction of the ratings in a group recommendation scenario in which groups are detected by clustering the users. Experimental results confirm that the approach to predict the ratings strongly influences the performance of a system and show that building predictions for each user, with respect to building predictions for a group, leads to great improvements in the accuracy of the recommendations. [ABSTRACT FROM AUTHOR]