Investigating Potential Factors Associated with Gender Discrimination in Collaborative Recommender Systems

Mansoury, Masoud; Abdollahpouri, Himan; Smith, Jessie Carney; Dehpanah, Arman; Pechenizkiy, Mykola; Mobasher, Bamshad

doi:10.48550/arxiv.2002.07786

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effect of gender in the e-commerce setting is still very nascent [63]. Particularly in the RS literature, scholars have expressed concerns about inconsistencies in the accuracy of recommendations between different genders [24][25][26]. For instance, Mansoury et al [24] argued that women get less accurate recommendations than men.…”

Section: Moderating Effect Of Gendermentioning

confidence: 99%

“…A growing body of research has raised concerns about the inconsistency in the precision of recommendations across genders [23][24][25][26]. Lack of empirical investigation on the impact of gender has been reported [27], despite the presence of substantial gender variations in online shopping speculated by IS scholars in terms of behaviours (e.g., online purchases) and attitudes (e.g., online trust) [28][29][30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Cognitive Absorption in Recommender System Reuse

2023

View full text Add to dashboard Cite

E-commerce is the trade of services and goods via electronic means such as the Internet. It is critical in today’s business and user experience. Most current e-commerce websites employ various technologies such as recommender systems to provide customers with personalised recommendations. Taking this as a cue, this study investigates the effect of cognitive absorption to estimate the holistic experience of recommender systems on shoppers’ intentions to reuse recommender systems. Data collected from 366 online shoppers were analysed using structural equation modelling to test the proposed hypotheses. The findings highlight that cognitive absorption directly and indirectly affects shoppers’ behavioural intentions to reuse recommender systems. The results also exposed the moderating effect of gender on shoppers’ behavioural intentions to reuse recommender systems. An importance-performance map analysis was also conducted to identify significant areas of improvement for e-vendors. This study contributes to advancing existing knowledge relevant to shoppers’ behavioural intentions to reuse recommender systems. The study also provides e-vendor managers with insights into online shoppers’ decision making.

show abstract

Section: Moderating Effect Of Gendermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Role of Cognitive Absorption in Recommender System Reuse

2023

View full text Add to dashboard Cite

show abstract

“…Due to these biases, it can not represent the entire population, and due to this, the results produced by recommender systems are biased, so there is an utmost need to solve this problem. The most common types of biases are gender bias [9,18], racial bias [19], selection bias [20,24], exposure bias [28,31], position bias [8,11], and popularity bias [4,5,12,27,30]. The focus of this paper is on popularity bias.…”

Section: Related Workmentioning

confidence: 99%

“…Although recommender systems are quite popular, there are concerns regarding the fairness of these systems amongst the research community. Recommender systems primarily face fairness issues at two levels, user-level [9,18] and item level [20,24]. This paper considers the most important fairness issue, namely the popularity bias at the item level.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Boosting Technique to Mitigate Popularity Bias in Recommender System

Gangwar,

Jain

2021

Preprint

View full text Add to dashboard Cite

The observed ratings in most recommender systems are subjected to popularity bias and are thus not randomly missing. Due to this, only a few popular items are recommended, and a vast number of non-popular items are hardly recommended. Not suggesting the non-popular items lead to fewer products dominating the market and thus offering fewer opportunities for creativity and innovation. In the literature, several fair algorithms have been proposed which mainly focused on improving the accuracy of the recommendation system. However, a typical accuracy measure is biased towards popular items, i.e., it promotes better accuracy for popular items compared to non-popular items. This paper considers a metric that measures the popularity bias as the difference in error on popular items and non-popular items. Motivated by the fair boosting algorithm on classification, we propose an algorithm that reduces the popularity bias present in the data while maintaining accuracy within acceptable limits. The main idea of our algorithm is that it lifts the weights of the non-popular items, which are generally underrepresented in the data. With the help of comprehensive experiments on real-world datasets, we show that our proposed algorithm outperforms the existing algorithms on the proposed popularity bias metric. CCS CONCEPTS• Information Filtering Systems → Recommender systems.

show abstract