| Abstrakt: |
This study uses machine learning techniques to explore the relationships between contemporary sexist attitudes and demographic and socioeconomic factors. A total of 1110 Greek adults participated in the study from November 2021 to February 2022, recruited online through undergraduate psychology students using network sampling. The sample comprised 67.48% women and 32.52% men aged 18–80 (M = 29.58, SD = 13.53). Demographic and socioeconomic factors such as age, marital status, whether or not children are present, education, occupation, and income were collected. Nine linear, nonlinear, and nonparametric machine learning models examined the impact of demographics and socioeconomic factors on modern sexism. After data-splitting (train dataset 50%, test dataset 50%), the nine machine learning models were trained to classify the top 33% scorers in the modern sexism scale. The model input variables were only demographics to avoid overlapping of inputs–outputs. A tenfold cross-validation method was then implemented in the training session to select the optimal machine learning model among the nine tested. The ctree algorithm was an optimal classification (Train-accuracy = 0.69, Test-accuracy = 0.71). The analysis revealed that gender, occupation, and having children significantly shaped contemporary sexist attitudes. The study highlights the need for targeted interventions and policies to promote gender equality and challenge harmful stereotypes. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink