Paper proposes GN-GloVe to learn gender-neutral word embeddings.
problem Inherit strong gender stereotypes in embeddings trained on human-generated corpora.
method Proposes a novel training procedure to isolate gender information in word vectors.
result GN-GloVe successfully isolates gender information without sacrificing functionality.
Study reveals unique gender disparities in Bangladeshi TV advertisements and talk shows.
problem Gender disparity and skin color distribution in Bangladeshi TV content.
method Computer Vision, machine learning, head pose, gender detection, skin color estimation.
result Lighter skin tones are less prevalent than darker in Bangladeshi TV, contrary to popular perception.
Study uses deep learning to predict gender and analyze HPV vaccine perceptions on Twitter.
problem Analyzing gender differences in public perceptions on HPV vaccine using social media data.
method Convolutional neural network model trained on Twitter text for gender prediction, then applied to HPV vaccine related tweets.
result Identified gender differences in public perceptions on HPV vaccine, consistent with previous studies.
Study shows gender bias in occupation classification tasks.
problem Gender bias in machine learning for occupation classification.
method Analyzed impact of explicit gender indicators in semantic representations of biographies.
result True positive rates differ between genders, correlating with existing gender imbalances.
Deep learning improves gender classification from handwriting.
problem Classifying gender from handwritten text.
method Convolutional Neural Network (CNN) for feature extraction and gender classification.
result Deep learning approach outperforms human examiners in gender classification accuracy.
Study evaluates gender bias in relation extraction systems.
problem Gender bias in relation extraction systems.
method Created WikiGenderBias dataset, evaluated systems for bias, analyzed bias mitigation techniques.
result NRE systems exhibit gender bias in predictions.
Improved neural model predicts gender from tweets.
problem Predicting gender from Twitter text.
method RNN model with attention, LSA-reduced n-gram features.
result Improved model achieves state-of-the-art performance on English tweets.
Reduces gender classification bias by learning race-invariant face representations.
problem Societal bias in gender recognition systems.
method Adversarially trained autoencoder model to learn race-invariant face representations.
result Achieved a significant drop of over 40% in racial bias surrogate metric with race invariant representations.
Study predicts gender from brain FC at multiple scales using deep learning and Bayesian methods.
problem Predicting gender from brain functional connectivity.
method Deep learning and Bayesian deep learning applied to brain FC data from 1003 healthy adults.
result Bayesian deep learning provides accurate predictions and uncertainty information.
Debiasing techniques can worsen gender bias in text classification, but a tweak improves both.
problem Debiasing techniques can inadvertently increase gender bias in text classification.
method Investigated traditional debiasing techniques and found they worsen bias. Suggested a minor adjustment.
result A minor adjustment to debiasing techniques can reduce gender bias while maintaining high classification accuracy.
Study quantifies gender bias in language models across 7 languages.
problem Measuring gender bias in language models across multiple languages.
method Curated dataset of politicians, multilingual language models, probing language models.
result Larger language models do not show significant gender bias compared to smaller ones.
Study measures gender bias in machine translation using multiple reference points.
problem Measuring and identifying gender bias in machine translation.
method Used an optimal non-biased translator, reference points from occupational statistics and survey.
result Found bias against both genders, but more against women, and found occupations have a greater effect than adjectives.
The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings traine…
New method neutralizes gender bias in word embeddings without losing semantic information.
problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.
This study examines gender bias in Dutch newspapers from 1950-1990 using word embeddings.
problem Examining gender bias in historical newspapers.
method Word embeddings to measure bias changes over time.
result Clear differences in gender bias and changes within newspapers over time.
Machine learning improves risk assessment for gender-based violence victims.
problem Accurately predicting recidivism risk in gender-based crime victims.
method Applied machine learning techniques to create models predicting recidivism risk.
result Proposed ML method outperforms classical statistical methods.
Paper improves gender detection on social media using deep learning.
problem Traditional classifiers struggle with social media data volume.
method Ensemble deep learning with multi-model architectures.
result Improved gender detection accuracy on social media posts.
Project improves gender-balanced pronoun resolution with BERT.
problem Challenging task in natural language understanding, especially for gendered pronouns.
method BERT-based approach to gender-balanced pronoun resolution.
result Achieved 92% F1 score with lower gender bias.
Predicts user age and gender on Tumblr using rich content.
problem Challenges in targeting specific demographic groups on Tumblr.
method Graph based and deep learning models, including network embedding, label propagation, CNN, and MLP.
result Significantly improved accuracy for age and gender predictions.
Paper finds gender classification accuracy varies by skin type, not ethnicity.
problem Unequal performance of face classification services across skin types and genders.
method Stability experiments, image manipulation, and post-hoc explanation techniques.
result Lip, eye, and cheek structure differences, not skin type, cause gender classification discrepancies.
Develops NFCF to reduce gender bias in social media recommendation systems.
problem Reduces gender bias in collaborative filtering systems on social media data.
method Pre-training and fine-tuning neural collaborative filtering with bias correction techniques.
result Achieves better performance and fairness in gender de-biased recommendations.
The gender wage gap varies significantly among women based on socio-economic characteristics.
problem Understanding the extent of gender inequality in earnings among U.S. women.
method High-dimensional wage regression and double lasso analysis of 2016 American Community Survey data.
result The gender wage gap varied substantially across women and was driven by marital status, having children, race, occupation, industry, and educational attainment.
Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in {\em word emb…
Predicts gender and age from mobile phone data for marketing.
problem Enhance marketing offers by predicting customer demographics.
method Machine learning algorithms applied to CDRs, CRM, and billing info.
result 85.6% accuracy in gender prediction, 65.5% in age prediction.
Reduces gender bias in patient notes while maintaining medical classification accuracy.
problem Bias in natural language processing of patient notes.
method Identifying and removing gendered language using BERT-based classifiers, then augmenting data to maintain performance.
result Minimal degradation in health condition classification tasks with data augmentation.
Study finds AI-generated financial advice influences life cycle investing patterns.
problem Understanding how AI-generated financial advice impacts life cycle investing.
method Sentiment analysis of prompts from AI-generated financial advice and simulation of lifetime effects.
result AI-generated financial advice leads to life cycle investing patterns, influenced by gender and AI experience.
Mitigates gender bias amplification in model predictions.
problem Gender bias amplification in model predictions.
method Posterior regularization to mitigate bias.
result Almost removes gender bias amplification in model predictions.
Dynamic weights improve multimodal emotion and gender recognition.
problem Improving performance in multiple classification tasks with a single model.
method Dynamic joint loss weights for multimodal emotion and gender recognition.
result Lower joint loss and better generalizability than static weights.
Study compares neural networks for age and gender recognition, revealing feature importance and robustness.
problem Understanding which facial features are used and how preprocessing affects deep neural networks for age and gender recognition.
method Compared four neural network architectures, evaluated preprocessing robustness, visualized prediction strategies.
result Suitable parameter initialization improves holistic perception of input, leading to state-of-the-art performance in gender recognition.
Study finds optimal board gender diversity for emissions performance.
problem Association between board gender diversity and emissions performance.
method Panel regressions, machine learning, explainable AI.
result Optimal board gender diversity for emissions performance is approximately 35%.
Study identifies clusters of EU countries with similar young mortality patterns.
problem Identify clusters of EU countries with similar mortality patterns in young population.
method Symbolic data analysis (SDA) with age, gender, and main causes of death dimensions.
result Identified clusters of EU countries with similar mortality patterns in young population.
New corpus improves coreference resolution by removing gender and number cues.
problem Challenges in resolving ambiguous pronoun references.
method Developed a new annotated corpus, introduced antecedent switching technique.
result Models perform poorly on ambiguous pronoun references, but antecedent switching improves performance.
Paper proposes a new classifier for gender detection in mobile telematics.
problem Detecting gender through mobile telematics data.
method Choquet fuzzy integral vertical bagging classifier combining random forest and rough set theory.
result Choquet fuzzy integral vertical bagging classifier outperforms other classifiers.
Develops fair machine learning models resistant to sensitive perturbations.
problem Ensuring model performance is invariant to sensitive attributes like gender and ethnicity.
method Distributionally robust optimization to enforce individual fairness.
result Demonstrates effectiveness on tasks prone to bias.
Study proposes an alternative method to measure societal biases using smoothed co-occurrence relations.
problem Measuring societal biases using word embeddings can introduce irrelevant concepts.
method Proposes an alternative approach using smoothed first-order co-occurrence relations.
result First-order approach shows higher correlations with actual gender bias statistics.
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
problem Gender bias in human decision-making on micro-lending platforms.
method Structural econometric model and machine learning algorithms trained on real-world data.
result Machine learning algorithms can mitigate both preference-based and belief-based biases.
Paper predicts demographics at finer geographic resolutions using geotagged tweets.
problem Limited traditional survey methods for demographics estimates at finer geographic resolutions.
method Adapting prior work to predict gender and race/ethnicity counts at the blockgroup-level.
result Achieves high correlations (0.671 for gender, 0.692 for race) compared to prior work.
The paper uses distance correlation for brain connectivity and a novel multi-task learning model for age prediction.
problem Estimating age-related gender differences in brain functional connectivity.
method Estimates functional connectivity using distance correlation and proposes a non-convex multi-task learning model.
result The proposed non-convex multi-task learning model outperforms other models in age prediction and gender-specific connectivity.
Study reduces gender bias in web data used for image recognition.
problem Gender bias in web data amplifies in machine learning models.
method Inject corpus-level constraints for calibrating structured prediction models.
result Bias amplification decreased by 47.5% and 40.5% for multilabel classification and visual semantic role labeling.
First place in ABC 2018: Classify bird gender from GPS trajectories.
problem Predicting the gender of shearwaters from GPS navigation data.
method Ensemble of Gradient Boosting Classifiers (CatBoost, LightGBM, XGBoost) with feature engineering.
result Ranked first among 74 teams in the Animal Behavior Challenge.
Paper tackles biases in AI embeddings from wild data.
problem Biases in AI embeddings from uncontrolled data.
method Measures biases using social psychology word lists, observes gender bias in occupations, demonstrates simple projection to reduce bias.
result Simple projection significantly reduces embedding biases.
Neural models use default reasoning for number and gender assignment tasks.
problem Understanding how neural language models make decisions for grammatical phenomena.
method Generalised Contextual Decomposition (GCD) to isolate semantic, syntactic, and bias-driven components of predictions.
result Models rely on default reasoning for tasks like number and gender assignment.
New method reduces gender bias in language models without harming performance.
problem Bias in language models learned from biased data.
method Causal analysis to identify problematic model components, followed by linear projection of weight matrices.
result DAMA significantly decreases bias in language models while maintaining performance.
Foundation models improve wage gap decomposition by capturing omitted career history factors.
problem Estimating wage disparities using incomplete career history data.
method Fine-tuning foundation models to mitigate omitted variable bias and estimate wage gaps.
result Foundation models can decompose gender wage gaps more accurately than traditional econometric methods.
Stochastic encoding improves gender classification of brain networks from UK Biobank data.
problem Complexity and bias in interpreting deep learning models of brain connectivity.
method Stochastic encoding in ensemble of CNNs, multivariate balancing algorithm.
result AUROC of 0.8459, with resting-state data more accurate than task data.
Study finds corporate boards with women appoint more women, leading to better profitability.
problem Influence of female board members on corporate profitability.
method Analysis of Japanese corporate boards and their interlocks.
result Corporate boards with women appoint more women, leading to higher profitability.
This study compares DR methods with kernel variations for face image analysis.
problem High dimensionality, noise, and correlation in data.
method Reviews and comparative study of PCA, LDA, KPCA, KLDA, SKPCA.
result SKPCA outperforms other methods in gender classification on face databases.
New technique reduces gender discrimination in credit lending models.
problem Bias and unfairness in credit lending predictions.
method Subgroup Threshold Optimizer (STO) technique.
result Reduces gender discrimination by over 90%.