Detecting race and gender bias in visual representation of AI on web search engines
Web search engines influence perception of social reality by filtering and ranking information. However, their outputs are often subjected to bias that can lead to skewed representation of subjects such as professional occupations or gender. In our paper, we use a mixed-method approach to investigate presence of race and gender bias in representation of artificial intelligence (AI) in image search results coming from six different search engines. Our findings show that search engines prioritize anthropomorphic images of AI that portray it as white, whereas non-white images of AI are present only in non-Western search engines. By contrast, gender representation of AI is more diverse and less skewed towards a specific gender that can be attributed to higher awareness about gender bias in search outputs. Our observations indicate both the the need and the possibility for addressing bias in representation of societally relevant subjects, such as technological innovation, and emphasize the importance of designing new approaches for detecting bias in information retrieval systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RetrievalInformation RetrievalRetrievalSimilar Papers 제목 키워드 기반
Towards Reducing Bias in Gender Classification
Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race inv…
BIG-bench Machine LearningClassificationGender ClassificationGeneral ClassificationAssessing Intersectional Bias in Representations of Pre-Trained Image Recognition Models
Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the r…
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model
Ethical intervention prompting has emerged as a tool to counter demographic biases of text-to-image generative AI models. Existing solutions either require to retrain the model or struggle to generate images that reflect…
AttributeImage GenerationA Multibias-mitigated and Sentiment Knowledge Enriched Transformer for Debiasing in Multimodal Conversational Emotion Recognition
Multimodal emotion recognition in conversations (mERC) is an active research topic in natural language processing (NLP), which aims to predict human's emotional states in communications of multiple modalities, e,g., natu…
Emotion RecognitionMultimodal Emotion RecognitionMarkedness in Visual Semantic AI
We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or ethnicity. Given the option to label an im…