Automated content analysis of cultural Diversity Perspectives in Annual Reports (DivPAR): Development, validation, and future research agenda.

Objective: In this article, we present a digital tool (Diversity Perspectives in Annual Reports [DivPAR]) for automated content analysis of annual reports, designed to identify the presence of three cultural diversity perspectives-the Moral, Market, and Innovation perspectives-based on earlier work by Ely and Thomas (2001). Method: In Study 1, we describe the development and validation of the instrument, through an iterative procedure in which manual annotation of independent subsamples (n = 24, 25) by human coders was compared to the computer coding in subsequent rounds, until sufficient agreement was reached. In Study 2, we illustrate the type of data that the script generates, by analyzing the prevalence of the three perspectives in annual reports of 55 Dutch organizations over a period of 2 decades (1999-2018; n = 937). Results: Our findings confirm that DivPAR is sufficiently reliable for use in future research. In Study 2, we show that among Dutch organizations, the moral perspective is most prevalent, but the market and innovation perspectives are increasing in popularity. Conclusion: DivPAR can be used to analyze the prevalence and longitudinal development of diversity perspectives in organizational communication. It enables scholars to draw comparisons across different sectors, regions, or countries, to study how diversity perspectives correlate with societal developments, and to uncover the (lack of) relationships between diversity communication and diversity outcomes. Directions for future research are discussed at the end of the article. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Reliable or not? An automated classification of webpages about early childhood vaccination using supervised machine learning.

OBJECTIVE: To investigate the applicability of supervised machine learning (SML) to classify health-related webpages as 'reliable' or 'unreliable' in an automated way. METHODS: We collected the textual content of 468 different Dutch webpages about early childhood vaccination. Webpages were manually coded as 'reliable' or 'unreliable' based on their alignment with evidence-based vaccination guidelines. Four SML models were trained on part of the data, whereas the remaining data was used for model testing. RESULTS: All models appeared to be successful in the automated identification of unreliable (F1 scores: 0.54-0.86) and reliable information (F1 scores: 0.82-0.91). Typical words for unreliable information are 'dr', 'immune system', and 'vaccine damage', whereas 'measles', 'child', and 'immunization rate', were frequent in reliable information. Our best performing model was also successful in terms of out-of-sample prediction, tested on a dataset about HPV vaccination. CONCLUSION: Automated classification of online content in terms of reliability, using basic classifiers, performs well and is particularly useful to identify reliable information. PRACTICE IMPLICATIONS: The classifiers can be used as a starting point to develop more complex classifiers, but also warning tools which can help people evaluate the content they encounter online.

Biased media? How news content influences age discrimination claims.

Information distributed via the news media is acknowledged as a potential source of negative beliefs about, and biased behaviors toward, older workers. Focusing on the Netherlands, the current study explains age discrimination claims filed by older workers by investigating the impact of visibility and media stereotypes of older workers in the news media, while controlling for real-world events and older workers' expectations of unemployment (2004-2014). The results, based on time-series analysis, reveal that the visibility of older workers in the news media is associated with higher levels of age discrimination claims. This effect can be partly explained with the visibility of the negative media stereotype that older workers experience health problems in the content of news coverage. Furthermore, unemployment expectations decreased the number of age discrimination claims. These results offer support for the notion that the news environment is a source of variation in the experience of age discrimination at the workplace.

More or less diverse: An assessment of the effect of attention to media salient company types on media agenda diversity in Dutch newspaper coverage between 2007 and 2013.

This study on news coverage of highly visible company types in a Dutch daily quality newspaper (NRC Handelsblad; N = 14,363), during the economic crisis (2007-2013), shows that attention to banks (and to a lesser extent also to the automobile and components industry) had a structural negative influence on media agenda diversity. The majority of the other salient company types had a significant positive impact on diversity. These results suggest that banks attracted attention at the expense of more varied, diverse coverage during the crisis. Our findings extend knowledge of agenda-building dynamics in relation to organizational news by considering characteristics of the broader media agenda. We discuss our findings in light of causes and consequences of media coverage of salient businesses.