Guidance on how to validate computational text-based measures of social science constructs is fragmented. Whereas scholars are generally acknowledging the importance of validating their text-based measures, they often lack common terminology and a unified framework to do so. This paper introduces a new validation framework called ValiTex, designed to assist scholars to measure social science constructs based on textual data. The framework draws on a long-established tradition within psychometrics while extending the framework for the purpose of computational text analysis. ValiTex consists of two components, a conceptual model, and a dynamic checklist. Whereas the conceptual model provides a general structure along distinct phases on how to approach validation, the dynamic checklist defines specific validation steps and provides guidance on which steps might be considered recommendable (i.e., providing relevant and necessary validation evidence) or optional (i.e., useful for providing additional supporting validation evidence. The utility of the framework is demonstrated by applying it to a use case of detecting sexism from social media data.
Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited with promoting core features of the construct over spurious artifacts that happen to correlate with it. Yet, over-relying on core features may lead to unintended model bias. Especially, construct-driven CAD -- perturbations of core features -- may induce models to ignore the context in which core features are used. Here, we test models for sexism and hate speech detection on challenging data: non-hateful and non-sexist usage of identity and gendered terms. In these hard cases, models trained on CAD, especially construct-driven CAD, show higher false-positive rates than models trained on the original, unperturbed data. Using a diverse set of CAD -- construct-driven and construct-agnostic -- reduces such unintended bias.
Measures of algorithmic fairness often do not account for human perceptions of fairness that can substantially vary between different sociodemographics and stakeholders. The FairCeptron framework is an approach for studying perceptions of fairness in algorithmic decision making such as in ranking or classification. It supports (i) studying human perceptions of fairness and (ii) comparing these human perceptions with measures of algorithmic fairness. The framework includes fairness scenario generation, fairness perception elicitation and fairness perception analysis. We demonstrate the FairCeptron framework by applying it to a hypothetical university admission context where we collect human perceptions of fairness in the presence of minorities. An implementation of the FairCeptron framework is openly available, and it can easily be adapted to study perceptions of algorithmic fairness in other application contexts. We hope our work paves the way towards elevating the role of studies of human fairness perceptions in the process of designing algorithmic decision making systems.
To effectively tackle sexism online, research has focused on automated methods for detecting sexism. In this paper, we use items from psychological scales and adversarial sample generation to 1) provide a codebook for different types of sexism in theory-driven scales and in social media text; 2) test the performance of different sexism detection methods across multiple data sets; 3) provide an overview of strategies employed by humans to remove sexism through minimal changes. Results highlight that current methods seem inadequate in detecting all but the most blatant forms of sexism and do not generalize well to out-of-domain examples. By providing a scale-based codebook for sexism and insights into what makes a statement sexist, we hope to contribute to the development of better and broader models for sexism detection, including reflections on theory-driven approaches to data collection.
During the past decades the importance of soft skills for labour market outcomes has grown substantially. This carries implications for labour market inequality, since previous research shows that soft skills are not valued equally across race and gender. This work explores the role of soft skills in job advertisements by drawing on methods from computational science as well as on theoretical and empirical insights from economics, sociology and psychology. We present a semi-automatic approach based on crowdsourcing and text mining for extracting a list of soft skills. We find that soft skills are a crucial component of job ads, especially of low-paid jobs and jobs in female-dominated professions.Our work shows that soft skills can serve as partial predictors of the gender composition in job categories and that not all soft skills receive equal wage returns at the labour market. Especially "female" skills are associated with wage penalties. Our results expand the growing literature on soft skills and highlight the importance of soft skills for occupational gender segregation at labour markets.