Descriptions of women are longer than that of men: An analysis of gender portrayal prompts in Stable Diffusion

• URL: http://arxiv.org/abs/2411.18994v1
• Date: Thu, 28 Nov 2024 08:48:05 GMT
• Title: Descriptions of women are longer than that of men: An analysis of gender portrayal prompts in Stable Diffusion
• Authors: Yan Asadchy, Maximilian Schich,
• Abstract summary: We analyze over 1.8 million prompts depicting men and women on Discord. We find classic stereotypes in which men are described using dominant qualities such as "strong" and "rugged" Women are represented with concepts related to body and submission: "beautiful", "pretty", etc.
• Score: 0.0
• License:
• Abstract: Generative AI for image creation emerges as a staple in the toolkit of digital artists, visual designers, and the general public. Social media users have many tools to shape their visual representation: image editing tools, filters, face masks, face swaps, avatars, and AI-generated images. The importance of the right profile image can not be understated: It is crucial for creating the right first impression, sustains trust, and enables communication. Conventionally correct representation of individuals, groups, and collectives may help foster inclusivity, understanding, and respect in society, ensuring that diverse perspectives are acknowledged and valued. While previous research revealed the biases in large image datasets such as ImageNet and inherited biases in the AI systems trained on it, within this work, we look at the prejudices and stereotypes as they emerge from textual prompts used for generating images on Discord using the StableDiffusion model. We analyze over 1.8 million prompts depicting men and women and use statistical methods to uncover how prompts describing men and women are constructed and what words constitute the portrayals of respective genders. We show that the median male description length is systematically shorter than the median female description length, while our findings also suggest a shared practice of prompting regarding the word length distribution. The topic analysis suggests the existence of classic stereotypes in which men are described using dominant qualities such as "strong" and "rugged". In contrast, women are represented with concepts related to body and submission: "beautiful", "pretty", etc. These results highlight the importance of the original intent of the prompting and suggest that cultural practices on platforms such as Discord should be considered when designing interfaces that promote exploration and fair representation.

Related papers

• Computational Analysis of Gender Depiction in the Comedias of Calderón de la Barca [6.978406757882009]
  We develop methods to study gender depiction in the non-religious works (comedias) of Pedro Calder'on de la Barca. We gather insights from a corpus of more than 100 plays by using a gender classifier and applying model explainability (attribution) methods. We find that female and male characters are portrayed differently and can be identified by the gender prediction model at practically useful accuracies.
  arXiv  Detail & Related papers  (2024-11-06T13:13:33Z)
• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
  We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
  arXiv  Detail & Related papers  (2024-02-16T21:32:27Z)
• Stable Diffusion Exposed: Gender Bias from Prompt to Image [25.702257177921048]
  This paper introduces an evaluation protocol that analyzes the impact of gender indicators at every step of the generation process on Stable Diffusion images. Our findings include the existence of differences in the depiction of objects, such as instruments tailored for specific genders, and shifts in overall layouts.
  arXiv  Detail & Related papers  (2023-12-05T10:12:59Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models [6.92043136971035]
  We investigate how multimodal models handle diverse gender identities. We find certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised. These improvements could pave the way for a future where change is led by the affected community.
  arXiv  Detail & Related papers  (2023-05-26T16:28:49Z)
• Auditing Gender Presentation Differences in Text-to-Image Models [54.16959473093973]
  We study how gender is presented differently in text-to-image models. By probing gender indicators in the input text, we quantify the frequency differences of presentation-centric attributes. We propose an automatic method to estimate such differences.
  arXiv  Detail & Related papers  (2023-02-07T18:52:22Z)
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale [61.555788332182395]
  We investigate the potential for machine learning models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects.
  arXiv  Detail & Related papers  (2022-11-07T18:31:07Z)
• How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? [67.97752431429865]
  We study the effect on the diversity of the generated images when adding ethical intervention. Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender'
  arXiv  Detail & Related papers  (2022-10-27T07:32:39Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.