Quality & Quantity最新文献

Gender bias in machine learning: insights from official labour statistics and textual analysis. 机器学习中的性别偏见：来自官方劳工统计和文本分析的见解。

Quality & Quantity Pub Date : 2026-01-01 Epub Date: 2025-07-08 DOI: 10.1007/s11135-025-02261-0

Orfeas Menis-Mastromichalakis, George Filandrianos, Maria Symeonaki, Glykeria Stamatopoulou, Dimitris Parsanoglou, Giorgos Stamou

{"title":"Gender bias in machine learning: insights from official labour statistics and textual analysis.","authors":"Orfeas Menis-Mastromichalakis, George Filandrianos, Maria Symeonaki, Glykeria Stamatopoulou, Dimitris Parsanoglou, Giorgos Stamou","doi":"10.1007/s11135-025-02261-0","DOIUrl":"10.1007/s11135-025-02261-0","url":null,"abstract":"The interplay between technology and societal norms often reveals a troubling reality: machine learning systems not only reflect existing gender stereotypes but can also amplify and entrench them, making these biases harder to detect and address. This paper adopts an interdisciplinary approach, combining quantitative and qualitative methods with recent technological advancements, such as machine learning techniques for textual analysis and computational linguistics, to offer a new framework for understanding occupational gender bias in machine learning. The study is motivated by persistent gender inequalities in the labour market and rising concerns about gendered algorithmic bias, as outlined in the European Commission's Gender Equality Strategy 2020-2025. Focusing on language translation technologies, the research explores how machine learning may perpetuate or amplify gender stereotypes, aiming to foster more inclusive digital systems aligned with EU strategic goals. More specifically, it investigates occupational gender segregation and its manifestations in various forms of gender bias in machine learning across English, French, and Greek. The study introduces a classification of gender biases in machine learning, providing insights into professional areas needing intervention to address gender imbalances and identifying enduring stereotypical representations in textual data. To support this, statistical analysis is conducted to explore gender variations in occupations over the past thirteen years, using official data and international classifications such as the International Standard Classification of Occupations (ISCO-08). Moreover, gendered occupational distributions are extracted from 200,920 text instances in the three languages, revealing significant discrepancies between official labour statistics and the training data.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"60 1","pages":"619-653"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12920283/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147272537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a unified approach to formal "risk of bias" assessments for causal and descriptive inference. 对因果推理和描述性推理的正式“偏见风险”评估的统一方法。

Quality & Quantity Pub Date : 2026-01-01 Epub Date: 2026-03-16 DOI: 10.1007/s11135-026-02687-0

O L Pescott, R J Boyd, G D Powney, G B Stewart

{"title":"Towards a unified approach to formal \"risk of bias\" assessments for causal and descriptive inference.","authors":"O L Pescott, R J Boyd, G D Powney, G B Stewart","doi":"10.1007/s11135-026-02687-0","DOIUrl":"10.1007/s11135-026-02687-0","url":null,"abstract":"Statistics is sometimes described as the science of reasoning under uncertainty. Statistical models provide one view of this uncertainty, but what is frequently neglected is the \"invisible\" portion of uncertainty: that assumed not to exist once a model has been fitted to some data. Systematic errors, i.e. bias, in data relative to some model and inferential goal can seriously undermine research conclusions, and qualitative and quantitative techniques have been created across several disciplines to quantify and generally appraise such potential biases. Perhaps best known are so-called \"risk of bias\" assessment instruments used to investigate the likely quality of randomised controlled trials in medical research. However, the logic of assessing the risks caused by various types of systematic error to statistical arguments applies far more widely. This logic applies even when statistical adjustment strategies for potential biases are used, as these frequently make assumptions (e.g. data \"missing at random\") that can rarely be empirically guaranteed. Mounting concern about such situations can be seen in the increasing calls for greater consideration of biases caused by nonprobability sampling in descriptive inference (e.g. in survey sampling), and the statistical generalisability of in-sample causal effect estimates in causal inference. Both of these relate to the consideration of model-based and wider uncertainty when presenting research conclusions from models. Given that model-based adjustments are never perfect, we argue that qualitative risk of bias reporting frameworks for both descriptive and causal inferential arguments should be further developed and made mandatory by journals and funders. It is only through clear statements of the limits to statistical arguments that consumers of research can fully judge their value for any given application.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"60 3","pages":"10473-10488"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13230286/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148165357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unraveling honest responding: a systematic review on the effectiveness of social desirability bias reduction methods in survey research. 揭示诚实回应：调查研究中社会期望偏差减少方法有效性的系统回顾。

Quality & Quantity Pub Date : 2026-01-01 Epub Date: 2026-03-14 DOI: 10.1007/s11135-026-02664-7

Emma Zaal, Yfke Ongena, Nina van der Velden, Dan Loughnan, John Hoeks

{"title":"Unraveling honest responding: a systematic review on the effectiveness of social desirability bias reduction methods in survey research.","authors":"Emma Zaal, Yfke Ongena, Nina van der Velden, Dan Loughnan, John Hoeks","doi":"10.1007/s11135-026-02664-7","DOIUrl":"10.1007/s11135-026-02664-7","url":null,"abstract":"Social Desirability Bias (SDB), the tendency of respondents to present themselves in socially acceptable terms, poses serious challenges for the validity of survey research. This study systematically reviewed the effectiveness of methods aimed at reducing SDB. Searches in Scopus and PsycINFO of publications from 2017 to 2021 identified a total of 121 experiments in 79 peer-reviewed papers. These experiments, conducted in over 20 Western countries, employed 13 SDB-reduction methods across more than 17 behavioral or cognitive topics. Based on 10 quality measures, the methodological quality of these experiments was typically high. There was considerable variability in the frequency of SDB-reduction methods being used and their effectiveness. The most common methods were list experiments, probability-based techniques (RRT/NRRT), face-saving strategies, survey mode, and proxy reporting. Overall, in 55% of experiments SDB was significantly reduced, with face-saving strategies demonstrating the highest efficacy. Future research should aim at replicating these findings in a wider range of (societally relevant) topics and more comprehensively testing promising less explored methods. This review highlights the importance of continuing to refine and test SDB reduction techniques to improve survey data quality.Supplementary information: The online version contains supplementary material available at 10.1007/s11135-026-02664-7.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"60 3","pages":"10359-10391"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13230293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148165383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unlocking insights: assessing the quality of conventional and image-based responses on books at home in an online mobile survey. 解锁见解：在一项在线移动调查中评估传统和基于图像的家庭图书反馈的质量。

Quality & Quantity Pub Date : 2026-01-01 Epub Date: 2026-01-03 DOI: 10.1007/s11135-025-02519-7

Patricia A Iglesias

{"title":"Unlocking insights: assessing the quality of conventional and image-based responses on books at home in an online mobile survey.","authors":"Patricia A Iglesias","doi":"10.1007/s11135-025-02519-7","DOIUrl":"10.1007/s11135-025-02519-7","url":null,"abstract":"Despite growing interest in collecting photos within online surveys, little is known about the quality of visual data and its comparison with data obtained through conventional requests. To address this gap, a self-administered online mobile survey targeting parents of children attending primary school in Spain was conducted through the Netquest opt-in panel in 2023. The survey gathered information about books in respondents' homes through photos and conventional questions. First, a review of previous research using conventional questions, photos, and other emerging data types was conducted to identify indicators suitable to evaluate the quality of the information about books at home collected through conventional and image-based formats. Second, most of these indicators to measure quality were estimated. Results reveal important measurement errors in conventional questions, while photos submitted by respondents are generally in line and can be classified. However, concrete information of interest about the books, such as the intended audience or languages, is often difficult to extract from photos. When comparing quality, conventional answers provide more information about the items asked than photos, but photos have the potential to provide additional insights, such as book titles. Overall, while collecting and analyzing photos sent through surveys presents challenges, their integration into surveys offers unique opportunities to enrich data collection methods.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"60 2","pages":"6619-6643"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083421/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147724385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

It's a long way to the top (if you wanna biplot): a back-to-basics perspective on the implementation of principal component biplots in R. 这是一个很长的路要走到顶端（如果你想要双标图）：在R中实现主成分双标图的回归基本视角。

Quality & Quantity Pub Date : 2026-01-01 Epub Date: 2025-07-26 DOI: 10.1007/s11135-025-02266-9

Ettore Settanni, Jagjit Singh Srai

引用次数: 0

Assessing the sustainability of fiscal imbalance and public debt in India: evidence from novel asymmetric and fourier approaches 评估印度财政失衡和公共债务的可持续性：来自新型非对称和傅立叶方法的证据

Quality & Quantity Pub Date : 2025-12-18 DOI: 10.1007/s11135-025-02493-0

Masroor Ahmad, Arif Mohd Khah

引用次数: 0

‘Kaleidoscopic gazing’ techniques: the practice of creative data analysis innovation “万花筒式凝视”技术：创造性数据分析创新的实践

Quality & Quantity Pub Date : 2025-08-12 DOI: 10.1007/s11135-025-02319-z

Melanie Beckett, Gillian Forrester

{"title":"‘Kaleidoscopic gazing’ techniques: the practice of creative data analysis innovation","authors":"Melanie Beckett, Gillian Forrester","doi":"10.1007/s11135-025-02319-z","DOIUrl":"https://doi.org/10.1007/s11135-025-02319-z","url":null,"abstract":"This article offers new insights for researchers wishing to practically analyse qualitative data both manually and creatively. Drawing on a longitudinal, constructivist grounded theory PhD study about students’ transition experiences from Further to Higher Education, the article offers the innovative model of ‘Kaleidoscope Gazing’ to provide an account of how complex datasets might be puzzled through and, as such, augments current approaches to grounded theory. The kaleidoscope metaphor is a fresh way of considering social phenomenon and can be used as a tool for grasping the complexity, ambiguity, and fluidity of individual’s situated experiences in multifarious contexts. It facilitates the piecing together of patterns of similarity and difference in the reported experiences of participants and helps to ‘visualise’ the myriad of factors affecting their worlds. Manually working with complex datasets offers new ways of perceiving connections within them and affords more nuanced and deeper understandings. This model is intended to be used as a training tool for both novice researchers seeking guidance about how to understand and analyse their qualitative datasets, and those more experienced researchers looking for alternative avenues through which to explore their data in more depth.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"60 1","pages":"1839-1857"},"PeriodicalIF":0.0,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11135-025-02319-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147901990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ChatGPT in thematic analysis: Can AI become a research assistant in qualitative research? 专题分析中的ChatGPT: AI能否成为定性研究的研究助手？

Quality & Quantity Pub Date : 2025-06-02 DOI: 10.1007/s11135-025-02165-z

Kien Nguyen‐Trung

{"title":"ChatGPT in thematic analysis: Can AI become a research assistant in qualitative research?","authors":"Kien Nguyen‐Trung","doi":"10.1007/s11135-025-02165-z","DOIUrl":"https://doi.org/10.1007/s11135-025-02165-z","url":null,"abstract":"Abstract Despite an emerging body of scholarship on applying generative AI (GenAI) to qualitative data analysis, this area remains underdeveloped. This article evaluates how GenAI can support thematic analysis using a publicly available interview dataset from Lumivero. It introduces Guided AI Thematic Analysis (GAITA), an adaptation of King et al.’s (2018) Template Analysis. This framework positions researchers as a reflexive instrument and intellectual leader while thoroughly guiding GPT-4 in four stages: data familiarization; preliminary coding; template formation and finalization; and theme development. Additionally, the article proposes the ACTOR framework, a simple approach to combining different effective prompting techniques when working with GenAI for qualitative research purposes. Findings reveal GenAI’s capacity for analyzing the data, generating codes, subcodes, clusters, and themes, along with its adaptive learning and interactive assistance in organizing unstructured data and developing trustworthiness. However, this model has some key limitations in terms of its restricted context window for processing large datasets, its inconsistent outputs requiring multiple prompt attempts, the need to move across workspaces, and the lack of relevant training data for qualitative research purposes.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"59 6","pages":"4945-4978"},"PeriodicalIF":0.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11135-025-02165-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147912326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 41

Best practices for studies using digital data donation. 使用数字数据捐赠进行研究的最佳实践。

Quality & Quantity Pub Date : 2025-01-01 Epub Date: 2024-10-08 DOI: 10.1007/s11135-024-01983-x

Thijs C Carrière, Laura Boeschoten, Bella Struminskaya, Heleen L Janssen, Niek C de Schipper, Theo Araujo

{"title":"Best practices for studies using digital data donation.","authors":"Thijs C Carrière, Laura Boeschoten, Bella Struminskaya, Heleen L Janssen, Niek C de Schipper, Theo Araujo","doi":"10.1007/s11135-024-01983-x","DOIUrl":"10.1007/s11135-024-01983-x","url":null,"abstract":"Digital trace data form a rich, growing source of data for social sciences and humanities. Data donation offers an innovative and ethical approach to collect these digital trace data. In data donation studies, participants request a copy of the digital trace data a data controller (e.g., large digital social media or video platforms) collected about them. The European Union's General Data Protection Regulation obliges platforms to provide such a copy. Next, the participant can choose to share (part of) this data copy with the researcher. This way, the researcher can obtain the digital trace data of interest with active consent of the participant. Setting up a data donation study involves several steps and considerations. If executed poorly, these steps might threaten a study's quality. In this paper, we introduce a workflow for setting up a robust data donation study. This workflow is based on error sources identified in the Total Error Framework for data donation by Boeschoten et al. (2022a) as well as on experiences in earlier data donation studies by the authors. The workflow is discussed in detail and linked to challenges and considerations for each step. We aim to provide a starting point with guidelines for researchers seeking to set up and conduct a data donation study.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"59 Suppl 1","pages":"389-412"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11971172/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143796904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is a single model enough? The systematic comparison of computational approaches for detecting populist radical right content. 单一模型就足够了吗？检测民粹主义极右内容的计算方法的系统比较。

Quality & Quantity Pub Date : 2025-01-01 Epub Date: 2025-01-29 DOI: 10.1007/s11135-024-02034-1

Mykola Makhortykh, Ernesto de León, Clara Christner, Maryna Sydorova, Aleksandra Urman, Silke Adam, Michaela Maier, Teresa Gil-Lopez

{"title":"Is a single model enough? The systematic comparison of computational approaches for detecting populist radical right content.","authors":"Mykola Makhortykh, Ernesto de León, Clara Christner, Maryna Sydorova, Aleksandra Urman, Silke Adam, Michaela Maier, Teresa Gil-Lopez","doi":"10.1007/s11135-024-02034-1","DOIUrl":"10.1007/s11135-024-02034-1","url":null,"abstract":"The rise of populist radical right (PRR) ideas stresses the importance of understanding how individuals engage with PRR content online. However, this task is complicated by the variety of channels through which such engagement can take place. In this article, we systematically compare computational approaches for detecting PRR content in textual data. Using 66 dictionary, classic supervised machine learning, and deep learning (DL) models, we compare how these distinct approaches perform on the PRR detection task for three Germanophone test datasets and how their performance is affected by different modes of text preprocessing. In addition to individual models, we examine the performance of 330 ensemble models combining the above-mentioned approaches for the dataset with a particularly high volume of noise. Our findings demonstrate that the DL models, in combination with more computationally intense forms of preprocessing, show the best performance among the individual models, but it remains suboptimal in the case of more noisy datasets. While the use of ensemble models shows some improvement for specific modes of preprocessing, overall, it mostly remains on par with individual DL models, thus stressing the challenging nature of computational detection of PRR content.","PeriodicalId":49649,"journal":{"name":"Quality & Quantity","volume":"59 Suppl 2","pages":"1163-1207"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12055619/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144043246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0