Article
Computer Science, Information Systems
Chen Gao, Yong Li, Fuli Feng, Xiangning Chen, Kai Zhao, Xiangnan He, Depeng Jin
Summary: This paper proposes a more practical cross-domain recommendation method that protects user privacy by sharing only item information instead of user behavior data, and utilizes the representation power of neural networks for recommendation. Experimental results demonstrate that this method can achieve similar or even better performance than traditional cross-domain recommendation methods that directly share user-relevant data.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2022)
Article
Computer Science, Information Systems
Cheng-Hsing Yang, Chi-Yao Weng, Yu-Zhen Yang
Summary: Image privacy technology in cloud storage services is gaining importance, with researchers proposing thumbnail-preserving encryption methods to balance privacy and usability. The novel TPEIP method based on SPE enhances image privacy effectively, as confirmed by experimental results.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2022)
Article
Environmental Studies
Valerio Sbragaglia, Ricardo A. Correia, Enrico Di Minin
Summary: It is important for researchers to follow specific steps when utilizing social media data for research on illegal fishing, while also considering data privacy and ethical principles. The authors hope that their reflections will encourage more responsible use of social media and digital platforms among marine conservation scientists.
Article
Mathematics, Applied
Muhammad Azeem
Summary: This paper introduces the novel idea of using the exponential function of scrambling variable in quantitative randomized response models. Two new quantitative randomized response models based on exponential scrambling variable are proposed. It is found that the new randomized response models are more efficient than the existing ones. The mathematical properties of the mean estimator of the sensitive variable and the measures of privacy protection and efficiency are discussed.
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
(2023)
Article
Microbiology
Kadriye Inan Bektas, Aleyna Nalcaoglu, Halil Ibrahim Guler, Sabriye Canakci, Ali Osman Belduz
Summary: This study aimed to clarify the taxonomic positions of Anoxybacillus kamchatkensis DSM 14988(T) and Anoxybacillus ayderensis AB04(T) using whole-genome phylogenetic analysis, biochemical, and chemotaxonomic characteristics. The results showed that A. kamchatkensis DSM 14988(T) is a later heterotypic synonym of A. ayderensis AB04(T).
ARCHIVES OF MICROBIOLOGY
(2022)
Article
Microbiology
Kadriye Inan Bektas, Halil Ibrahim Guler, Sabriye Canakci, Ali Osman Belduz
Summary: In this study, the taxonomic positions of Anoxybacillus karvacharensis K1(T), Anoxybacillus kestanbolensis NCIMB 13971(T), Anoxybacillus flavithermus subsp. yunnanensis CCTCC AB2010187(T), and Anoxybacillus tengchongensis DSM 23211(T) were clarified using whole-genome phylogenetic analysis. The results suggest that A. karvacharensis K1(T) is a later heterotypic synonym of A. kestanbolensis NCIMB13971(T), and that A. flavithermus subsp. yunnanensis CCTCCAB 2010187(T) is a later heterotypic synonym of A. tengchongensis DSM 23211(T).
ARCHIVES OF MICROBIOLOGY
(2022)
Article
Multidisciplinary Sciences
Da-Zhi Sun
Summary: Vinoth et al.'s proposed authenticated key agreement scheme for industrial IoT applications did not successfully defend against user impersonation, device impersonation, replay, and desynchronization attacks, and could not maintain user privacy.
Article
Communication
David M. Markowitz
Summary: The study found that people tend to tell more lies when communicating through synchronous, distributed, and recordless media like phone and video chat. Lying rates are also associated with individual traits and deception motives.
HUMAN COMMUNICATION RESEARCH
(2022)
Article
Social Sciences, Mathematical Methods
Muhammad Azeem, Abdul Salam
Summary: In social surveys, optional randomized response models allow respondents to choose between reporting their true response or a scrambled response. This paper proposes an alternative procedure where respondents can choose whether or not to disclose their true response. Modified versions of three existing scrambling randomized response models are presented. The study finds that knowing the exact number of respondents choosing the scrambled response improves the efficiency of quantitative randomized response models without compromising respondent privacy, leading to improved overall quality.
METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES
(2023)
Article
Engineering, Multidisciplinary
Keke Zhang, Xiaofeng Liao, Qingguo Lu
Summary: This article discusses a decentralized constrained optimization problem over time-varying directed networks and proposes a privacy-protected decentralized dual averaging push algorithm to protect privacy and overcome network imbalances caused by directed networks.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Editorial Material
Substance Abuse
Joel Billieux, Lois Fournier
Summary: The present commentary aims to extend the work conducted by Karhulahti et al. (2022) by performing network analysis on the four gaming disorder assessment tools they studied. The analysis revealed a high degree of overlap among the items, suggesting that these tools measure substantially homogeneous constructs. These exploratory results challenge the notion of ontological diversity in the context of gaming disorder assessment and diagnosis.
ADDICTION RESEARCH & THEORY
(2023)
Editorial Material
Psychology, Clinical
Rachel A. Clutterbuck, Lucy A. Livingston, Punit Shah
Summary: This study responds to concerns raised about the validity of the Four-Item Mentalising Index (FIMI) and argues that its construct validity has been exaggerated. The researchers maintain that FIMI is conceptually and psychometrically reliable and provide suggestions for improving objectivity in future research.
PSYCHOLOGICAL ASSESSMENT
(2022)
Article
Microbiology
Nina V. Doronina, Alina A. Chemodurova, Denis S. Grouzdev, Veronika V. Koziaeva, Nadezhda V. Agafonova, Wenyu Shi, Linhuan Wu, Elena N. Kaparullina
Summary: Three novel facultatively methylotrophic bacteria isolated from activated sludges were characterized. They were classified as a new species of the genus Ancylobacter and four previously classified species were suggested to be reclassified under the genus Ancylobacter. The polyphasic analyses supported these reclassifications.
ANTONIE VAN LEEUWENHOEK INTERNATIONAL JOURNAL OF GENERAL AND MOLECULAR MICROBIOLOGY
(2023)
Editorial Material
Psychiatry
Leon Y. Xiao
Summary: China's strict restrictions on young people's participation in video gaming since September 2021 have enhanced consumer protection by effectively reducing underage players' monetary spending on games.
JOURNAL OF BEHAVIORAL ADDICTIONS
(2022)
Article
Statistics & Probability
Andreas Quatember
Summary: If direct questioning on sensitive variables leads to non-ignorable item-nonresponse and untruthful answering, the resulting estimator could be considerably biased. In such cases, indirect questioning designs that protect privacy by masking sensitive information can improve accuracy by increasing respondents' willingness to cooperate. This article demonstrates how the item count technique, an indirect questioning design, can substantially enhance estimation accuracy and reduce respondents' burden by utilizing available prior information. This makes it a stronger and more serious competitor to the commonly used direct questioning on sensitive attributes in empirical research.
METRON-INTERNATIONAL JOURNAL OF STATISTICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Ramon Ferri-Garcia, Luis Castro-Martin, Maria del Mar Rueda
Summary: This study examines the use of traditional methods and machine learning algorithms in online surveys, comparing their performance in different scenarios. The simulation study shows that machine learning algorithms can effectively reduce volunteer bias to a greater extent than traditional methods.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Mathematics, Applied
S. Martinez, M. Rueda, M. Illescas
Summary: This study proposes new calibrated estimators for quantiles and poverty measures, which combine calibration techniques with the incorporation of auxiliary variables and selection of optimal calibration points. The selection of such points is aimed at minimizing the asymptotic variance of the quantile estimator. Results from simulation studies using real data suggest that the proposed estimators perform well and can be considered as reasonable alternatives to other methods.
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
M. Rueda, B. Cobo, P. F. Perri
Summary: The paper discusses methods for analyzing multicategorical variables, particularly focusing on ordinal variables. It explores the theoretical framework for estimating ordinal category frequencies when data are obtained through the randomized response technique (RRT), and how to improve inferential efficiency using auxiliary information through the calibration approach. The performance of the proposed estimators is evaluated in a Monte Carlo simulation study.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Mathematics, Applied
Luis Castro-Martin, Mara del Mar Rueda, Ramon Ferri-Garcia
Summary: The convenience of online surveys has made them increasingly popular for data collection. However, this method often suffers from biased samples. To address this issue, methods like Statistical Matching and Propensity Score Adjustment (PSA) have been proposed. This study suggests combining both techniques and evaluates their performance using real datasets.
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2022)
Article
Multidisciplinary Sciences
Beatriz Cobo, Eva Castillo, Francisca Lopez-Torrecillas, Maria del Mar Rueda
Summary: The prevalence and frequency of criminal behavior is challenging to estimate due to social desirability bias. The randomized response approach shows potential in criminal justice research, especially when it comes to self-reported data. Our study on prison inmates indicates that self-reported criminal behavior is influenced by social desirability bias, and indirect questioning techniques have potential to advance policy formation in this field.
Article
Mathematics
Maria del Mar Rueda, Beatriz Cobo, Antonio Arcos
Summary: Randomized response techniques are widely used in research involving sensitive variables, but are not generally applied to examine relationships between a sensitive variable and other characteristics. This article proposes a design-based regression analysis for complex sample designs based on the unified RR approach, which was also used to analyse findings from a real-world survey, demonstrating its theoretical properties through simulation.
Article
Statistics & Probability
Ramon Ferri-Garcia, Maria del Mar Rueda
Summary: The development of new survey data collection methods, such as online surveys, has provided advantages for social studies in terms of cost reduction, immediate responses, and improved questionnaire possibilities. However, these methods are often affected by selection bias, leading to unreliable estimates. To address this issue, this study applies calibration and propensity score adjustment methods, using variable selection techniques to improve the accuracy and efficiency of estimates by carefully selecting variables and algorithms.
STATISTICAL PAPERS
(2022)
Article
Mathematics, Applied
Sergio Martinez, Maria del Mar Rueda, Maria Dolores Illescas
Summary: This work deals with the problem of selecting the calibration auxiliary vector that minimizes the asymptotic variance of the calibration estimator of distribution function. The optimal dimension of the optimal auxiliary vector is reduced considerably with respect to previous studies so that with a smaller set of points, the minimum of the asymptotic variance can be reached, which in turn allows to improve the efficiency of the estimates.
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
(2022)
Article
Mathematical & Computational Biology
Maria del Mar Rueda, Sara Pasadas-del-Amo, Beatriz Cobo Rodriguez, Luis Castro-Martin, Ramon Ferri-Garcia
Summary: Web surveys have become the main method of data collection in most countries, but face limitations in obtaining probability-based samples. Probability-based designs are the gold standard, but nonprobability samples can be useful in certain situations. This paper proposes a methodology for combining probability and nonprobability web survey samples, and demonstrates its effectiveness through simulation and empirical studies.
BIOMETRICAL JOURNAL
(2023)
Article
Statistics & Probability
Pier Francesco Perri, Eleni Manoli, Tasos C. Christofides
Summary: In this paper, the presence and impact of untruthful responses in sensitive surveys are studied. A procedure to detect liars is proposed, using direct and indirect questions. The study finds that untruthful responses can significantly affect the quality of data and subsequent analyses. The problem can be mitigated by adopting indirect questioning techniques.
STATISTICAL PAPERS
(2023)
Article
Mathematics
Maria del Mar Rueda, Sergio Martinez-Puertas, Luis Castro-Martin
Summary: This article discusses the estimation of finite population distribution function in non-probability surveys and proposes methods to mitigate selection bias, enhancing the accuracy and efficiency of the estimates.
Article
Health Care Sciences & Services
J. Fernando Vera, Carmen Cecilia Sanchez Zuleta, Maria del Mar Rueda
Summary: Survey calibration is a widely used method in medical research to estimate population mean or total score. Traditional calibration techniques may not work when qualitative variables are involved. This article proposes the use of linear calibration with multidimensional scaling-based set of continuous auxiliary variables, avoiding computational problems.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2023)
Article
Criminology & Penology
Mhairi A. Gibson, Eshetu Gurmu, Beatriz Cobo, Maria M. Rueda, Isabel M. Scott
Summary: Understanding the reliability of direct questioning survey methods for measuring attitudes towards intimate partner violence (IPV) is challenging. A study conducted in rural Ethiopia using a list randomization experiment (LRE) found that there was high but underreported support for wife-beating among some members of the community. This highlights the need for open dialogue to prevent violence against women from going undetected and unchanged.
JOURNAL OF INTERPERSONAL VIOLENCE
(2022)