Temporal Analysis and Gender Bias in Computing

• URL: http://arxiv.org/abs/2210.08983v1
• Date: Thu, 29 Sep 2022 00:29:43 GMT
• Title: Temporal Analysis and Gender Bias in Computing
• Authors: Thomas J. Misa
• Abstract summary: Many names change ascribed gender over decades: the "Leslie problem" This article identifies 300 given names with measurable "gender shifts" across 1925-1975. This article demonstrates, quantitatively, there is net "female shift" that likely results in the overcounting of women (and undercounting of men) in earlier decades.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent studies of gender bias in computing use large datasets involving automatic predictions of gender to analyze computing publications, conferences, and other key populations. Gender bias is partly defined by software-driven algorithmic analysis, but widely used gender prediction tools can result in unacknowledged gender bias when used for historical research. Many names change ascribed gender over decades: the "Leslie problem." Systematic analysis of the Social Security Administration dataset -- each year, all given names, identified by ascribed gender and frequency of use -- in 1900, 1925, 1950, 1975, and 2000 permits a rigorous assessment of the "Leslie problem." This article identifies 300 given names with measurable "gender shifts" across 1925-1975, spotlighting the 50 given names with the largest such shifts. This article demonstrates, quantitatively, there is net "female shift" that likely results in the overcounting of women (and undercounting of men) in earlier decades, just as computer science was professionalizing. Some aspects of the widely accepted 'making programming masculine' perspective may need revision.

Related papers

• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions [5.896505047270243]
  We introduce an additional gender category, i.e., "neutral", to study and address potential gender biases in large language models. We investigate the impact of adding birth years to enhance the accuracy of gender prediction.
  arXiv  Detail & Related papers  (2024-07-07T05:59:09Z)
• The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages [51.2321117760104]
  This paper describes the Gender-GAP Pipeline, an automatic pipeline to characterize gender representation in large-scale datasets for 55 languages. The pipeline uses a multilingual lexicon of gendered person-nouns to quantify the gender representation in text. We showcase it to report gender representation in WMT training data and development data for the News task, confirming that current data is skewed towards masculine representation.
  arXiv  Detail & Related papers  (2023-08-31T17:20:50Z)
• 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)
• MISGENDERED: Limits of Large Language Models in Understanding Pronouns [46.276320374441056]
  We evaluate popular language models for their ability to correctly use English gender-neutral pronouns. We introduce MISGENDERED, a framework for evaluating large language models' ability to correctly use preferred pronouns.
  arXiv  Detail & Related papers  (2023-06-06T18:27:52Z)
• Gender Bias in Big Data Analysis [0.0]
  It measures gender bias when gender prediction software tools are used in historical big data research. Gender bias is measured by contrasting personally identified computer science authors in the well-regarded DBLP dataset.
  arXiv  Detail & Related papers  (2022-11-17T20:13:04Z)
• Dynamics of Gender Bias in Computing [0.0]
  This article presents a new dataset focusing on formative years of computing as a profession (1950-1980) when U.S. government workforce statistics are thin or non-existent. It revises commonly held conjectures that gender bias in computing emerged during professionalization of computer science in the 1960s or 1970s.
  arXiv  Detail & Related papers  (2022-11-07T23:29:56Z)
• Gender Bias in Computing [0.0]
  It offers new quantitative data on the computing workforce prior to the availability of US Census data in the 1970s. A novel method of gender analysis is developed to estimate women's and men's participation in computing beginning in the 1950s.
  arXiv  Detail & Related papers  (2022-10-29T00:10:25Z)
• Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation [64.65911758042914]
  We investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models. Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains. These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.
  arXiv  Detail & Related papers  (2022-05-19T20:05:02Z)
• Theories of "Gender" in NLP Bias Research [0.0]
  We survey nearly 200 articles concerning gender bias in NLP. We find that the majority of the articles do not make their theorization of gender explicit. Many conflate sex characteristics, social gender, and linguistic gender in ways that disregard the existence and experience of trans, nonbinary, and intersex people.
  arXiv  Detail & Related papers  (2022-05-05T09:20:53Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

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.