Collaborative filtering (CF) techniques learn user and item embeddings from user-item interaction behaviors, and are commonly used in recommendation systems to help users find potentially desirable ...items. Most CF models optimize recommendation accuracy; however, they may lead to unwanted biases for particular demographic groups. Thus, we focus on learning fair representations of CF-based recommendations. We formulate this problem as an optimization task with two competing goals: embedding representations better meet accuracy requirements of recommendations, and simultaneously obfuscate information hidden in the embedding space, which is related to the users’ sensitive attributes for fairness. Here, the intuitive idea is to use fair representation learning from machine learning to train a classifier with a sensitive attribute predictor from the user side to satisfy the fairness goal. However, such fair machine learning models assume entity independence, which differs greatly from CF because users and items are correlated collaboratively via user-item behaviors. Therefore, sensitive user information can be exposed from the users’ preferred items. Consequently, defining only fairness constraints on users cannot achieve fairness in recommendation systems. In this paper, we propose FairCF framework for fairness-aware collaborative filtering. In particular, we first define fairness constraints in a fair embedding space, where both a user classifier and an item classifier are employed to fit the fairness constraints. We then design an item classifier without item sensitive labels. The proposed framework can be trained in an end-to-end manner under most embedding based CF models. Extensive experiments conducted on three datasets (MovieLens-100K, MovieLens-1M, and Lastfm-360K) clearly demonstrate the superiority of the proposed FairCF framework relative to various fairness metrics (i.e., performance of newly-trained classifiers) than other state-of-the-art fairness-aware CF models with less than 4% accuracy reduction.
Various imputation approaches have been proposed to address the issue of missing values in data mining and machine learning applications. To improve the accuracy of missing data imputation, this ...paper proposes a new method called DIFC by integrating the merits of decision tress and fuzzy clustering into an iterative learning approach. To compare the performance of the DIFC method against five effective imputation methods, extensive experiments are conducted on six widely used datasets with numerical and categorical missing data, and with various amounts and types of missing values. The experimental results show that the DIFC method outperforms other methods in terms of imputation accuracy. Further experiments on the effect of missing value types demonstrate the robustness of the DIFC method in dealing with different types of missing values. This paper contributes to missing data imputation research by providing an accurate and robust method.
The study of the relationships between information technology (IT), environmental organizational issues and firm performance is a cutting-edge research topic for the information systems (IS) ...community. However, at present we know very little about these relationships. Drawing on the perspective of IT-enabled organizational capabilities and the literature on organizations and the natural environment, our study introduces conceptually the construct organizational capability of proactive corporate environmental strategy to the IS field. We propose that IT capability may enable the implementation of a proactive environmental strategy and that this strategy could play a significant role in determining the business value of IT. Using structural equations modeling with data collected from 63 firms, we find that IT capability is an enabler of proactive environmental strategy and that this strategy plays a significant role in mediating the effects of IT on firm performance. Our study provides initial evidence on the role of IT in the implementation of proactive environmental practices. Our results suggest to IT executives that their decisions matter in shaping environmental sustainability, which in turn will generate business value from IT.
Software platforms’ success largely depends on complementors’ willingness to repeatedly invest their time and effort to the development of platform applications that attract users and increase the ...platform’s installed base. But how can platform providers encourage desirable behaviours by complementors (i.e., application developers) in the absence of formal roles and hierarchical control structures? Although previous studies of software-based platforms have identified openness as critical instrument at the macro (i.e., platform) level and have provided initial attempts to measure the construct, no research has been dedicated to comprehensively conceptualize and operationalize platform openness at the micro level from the perspective of application developers. To go beyond these preliminary findings and to theorize about the nature and effects of platform openness as perceived by application developers, we develop a construct called perceived platform openness (PPO). Drawing on recently advanced scale development methodologies, we conceptualize PPO as a multidimensional construct and empirically validate it with important consequent variables linked to developers’ continuous platform contributions. Empirical evidence from several rounds of qualitative and quantitative steps supports the conceptual validity of the construct and empirical relevance of the scale across different smartphone platform contexts (i.e., Apple iOS and Google Android). Researchers will benefit from the study’s systematic and comprehensive conceptualization of PPO, how it is measured, and how it relates to critical application developer beliefs and attitudes. Platform managers may use our results to target the underlying facets of PPO most likely to contribute to the platform’s long-term goals.
Editorial to the special issue on JCDL 2022 Mayr, Philipp; Hinze, Annika; Schaer, Philipp
International journal on digital libraries,
06/2024, Volume:
25, Issue:
2
Journal Article
Peer reviewed
Open access
This special issue features the selected works of authors who have presented papers at the 2022 iteration of the Joint Conference on Digital Libraries (JCDL) in Cologne, Germany. The motto of the ...conference was “Bridging Worlds” and was run as a fully hybrid event. Ten papers covering all aspects of Digital Libraries, namely Natural Language Processing, Information Retrieval, User Behavior, Scholarly Communication, Classification, Information Extraction are included in this issue.
The anonymity mechanism of bitcoin is favored by the society, which promotes its usage and development. An adversary should not be able to discover the relation between bitcoin addresses and bitcoin ...users to ensure effective privacy. However, the relation among bitcoin transactions can be used to analyze the bitcoin privacy information, which seriously jeopardizes the bitcoin anonymity. Herein, we describe the vulnerabilities associated with the anonymity mechanism of bitcoin, including the relation among bitcoin addresses and the relation among bitcoin users. Further, we demonstrate that the existing methods do not guarantee the comprehensiveness, accuracy, and efficiency of the analysis results. We propose a heuristic clustering method to judge the relation among bitcoin addresses and employ the Louvain method to discover the relation among bitcoin users. Subsequently, we construct an address-associated database of historical transactions and implement real-time updates. Extensive experiments are used to demonstrate the comprehensiveness, accuracy, and efficiency of the proposed scheme. Specifically, the proposed scheme reveals the privacy vulnerability associated with the blockchain technology. We expect that our scheme can be applied to improve the blockchain technology.
Conclusions
In this letter, the impact of network dimension, connectivity parameter, and the number of failure nodes on network capacity is quantified from the viewpoint of order. These results can ...provide some suggestions for designing the large-scale wireless networks with the ability to combat node failure.