In psychology, causal inference—both the transport from lab estimates to the real world and estimation on the basis of observational data—is often pursued in a casual manner. Underlying assumptions remain unarticulated; potential pitfalls are compiled in post-hoc lists of flaws. The field should move on to coherent frameworks of causal inference and generalizability that have been developed elsewhere.

The present study investigated interpersonal attraction from zero to long-term acquaintance in a real-life context. A social relations approach that distinguishes between perceiver effects (e.g., being a liker), target effects (e.g., being liked), and relationship effects (e.g., unique liking) of interpersonal attraction was applied. Fifty-four psychology freshmen judged each other when they encountered one another for the first time, and again after their first year of study, using large round-robin designs (1,431 dyads). Three main groups of findings were revealed. First, variability increased on all three levels of analysis, demonstrating a higher differentiation at long-term acquaintance. Second, social relations effects at zero acquaintance predicted the respective effects at long-term acquaintance, indicating rank-order stability. Third, reciprocity, assumed reciprocity, and meta-accuracy increased substantially, reflecting higher closeness and intimacy at long-term acquaintance. Results are in line with a dynamic social relations approach to stability and change in interpersonal attraction.

Algorithmic automatic item generation can be used to obtain large quantities of cognitive items in the domains of knowledge and aptitude testing. However, conventional item models used by template-based automatic item generation techniques are not ideal for the creation of items for non-cognitive constructs. Progress in this area has been made recently by employing long short-term memory recurrent neural networks to produce word sequences that syntactically resemble items typically found in personality questionnaires. To date, such items have been produced unconditionally, without the possibility of selectively targeting personality domains. In this article, we offer a brief synopsis on past developments in natural language processing and explain why the automatic generation of construct-specific items has become attainable only due to recent technological progress. We propose that pre-trained causal transformer models can be fine-tuned to achieve this task using implicit parameterization in conjunction with conditional generation. We demonstrate this method in a tutorial-like fashion and finally compare aspects of validity in human- and machine-authored items using empirical data. Our study finds that approximately two-thirds of the automatically generated items show good psychometric properties (factor loadings above .40) and that one-third even have properties equivalent to established and highly curated human-authored items. Our work thus demonstrates the practical use of deep neural networks for non-cognitive automatic item generation.