Psychological trait inferences from women’s clothing: human and machine prediction

Abstract

People use clothing to make personality inferences about others, and these inferences steer social behaviors. The current work makes four contributions to the measurement and prediction of clothing-based person perception: first, we integrate published research and open-ended responses to identify common psychological inferences made from clothes (Study 1). We find that people use clothes to make inferences about happiness, sexual interest, intelligence, trustworthiness, and confidence. Second, we examine consensus (i.e., interrater agreement) for clothing-based inferences (Study 2). We observe that characteristics of the inferring observer contribute more to the drawn inferences than the observed clothes, which entails low to medium levels of interrater agreement. Third, the current work examines whether a computer vision model can use image properties (i.e., pixels alone) to replicate human inferences (Study 3). While our best model outperforms a single human rater, its absolute performance falls short of reliability conventions in psychological research. Finally, we introduce a large database of clothing images with psychological labels and demonstrate its use for exploration and replication of psychological research. The database consists of 5000 images of (western) women’s clothing items with psychological inferences annotated by 25 participants per clothing item.

Comparison of face‐based and voice‐based first impressions in a Chinese sample

“…Face and voice cues are advantageous when people are trying to form a rapid and accurate first impression of a stranger. This is because, compared with other cues, such as individuals' behavioural responses (Falvello et al, 2015; Ferrari et al, 2020) and clothing (Fiore & DeLong, 1984; Pazda & Thorstenson, 2019; Rosenbusch et al, 2021), cues related to face (Todorov & Oh, 2021) and voice (Baus et al, 2019; McAleer et al, 2014; Wu et al, 2021) are processed rapidly. Moreover, they convey extensive biological and sociocultural information, as well as stable and distinct personal recognition (McAleer et al, 2014; South Palomares & Young, 2018).…”

Sustainability of Costume Appearance: Influence of Psychological and Social Values on the Bangladeshi Young Generation

“…Hereditary features such as gender, race, and physical development are also included. On a personal level, a costume and its appearance, will reveal information about the wearer’s values, behaviors, passions, and way of life, as well as social and psychological relations (Rosenbusch et al, 2020). The consumers’ costume appearance is very visible, causing people to shape perceptions or draw various cues about the user based on psychological influences.…”

Can Fashion Aesthetics be Studied Empirically? The Preference Structure of Everyday Clothing Choices

“…Secondly, the study aimed to see whether the liking and owning of each clothing style factor correlates with several individual differences measures, with a focus on personality variables (e.g., conscientiousness) that have been studied extensively in the past (for research on the individual differences in clothing styles, see Albright, Kenny, & Malloy [1988]; Borkenau & Liebler, [1992]; Johnson & Francis, [2006]; Stolovy [2021]; and Vazire, Naumann, Rentfrow, & Gosling [2008]). Thirdly, the study aimed to understand whether each clothing style factor is associated with certain color schemes, another important physical attribute 2 in characterizing clothing (for research on the association between certain clothing styles and certain colors, see Elliot & Niesta [2008]; Elliot et al [2010]; Feltman & Elliot [2011]; Frank & Gilovich [1988]; Maier et al [2013]; Elliot et al [2013]; Rosenbusch, Aghaei, Evans, & Zeelenberg [2021]; and Sidhu, Qualter, Higgs, & Guo [2021]). Lastly, the study aimed to assess whether the clothing style factors can be replicated with “liking but not owning” and “owning but not liking” preference rating data, given recent empirical works on the distinction between liking and wanting (Aharon et al, 2001; Berridge, Robinson, & Aldridge, 2009; Chatterjee & Vartanian, 2016).…”