From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets

• URL: http://arxiv.org/abs/2404.17874v1
• Date: Sat, 27 Apr 2024 12:10:10 GMT
• Title: From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets
• Authors: Manuel Tonneau, Diyi Liu, Samuel Fraiberger, Ralph Schroeder, Scott A. Hale, Paul Röttger,
• Abstract summary: Hate speech datasets have traditionally been developed by language. We evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We find that HS datasets for English, Arabic and Spanish exhibit a strong geo-cultural bias.
• Score: 10.264294331399434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural biases, as one language may be spoken in different countries home to different cultures. In this work, we evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We conduct a systematic survey of HS datasets in eight languages and confirm past findings on their English-language bias, but also show that this bias has been steadily decreasing in the past few years. For three geographically-widespread languages -- English, Arabic and Spanish -- we then leverage geographical metadata from tweets to approximate geo-cultural contexts by pairing language and country information. We find that HS datasets for these languages exhibit a strong geo-cultural bias, largely overrepresenting a handful of countries (e.g., US and UK for English) relative to their prominence in both the broader social media population and the general population speaking these languages. Based on these findings, we formulate recommendations for the creation of future HS datasets.

Related papers

• WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines [74.25764182510295]
  Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English. We introduce World Cuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points.
  arXiv  Detail & Related papers  (2024-10-16T16:11:49Z)
• BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla [0.0]
  This study presents BanStereoSet, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. Our dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty in profession, region, caste, and religion.
  arXiv  Detail & Related papers  (2024-09-18T02:02:30Z)
• CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark [68.21939124278065]
  Culturally-diverse multilingual Visual Question Answering benchmark designed to cover a rich set of languages and cultures. CVQA includes culturally-driven images and questions from across 30 countries on four continents, covering 31 languages with 13 scripts, providing a total of 10k questions. We benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-06-10T01:59:00Z)
• Global Voices, Local Biases: Socio-Cultural Prejudices across Languages [22.92083941222383]
  Human biases are ubiquitous but not uniform; disparities exist across linguistic, cultural, and societal borders. In this work, we scale the Word Embedding Association Test (WEAT) to 24 languages, enabling broader studies. To encompass more widely prevalent societal biases, we examine new bias dimensions across toxicity, ableism, and more.
  arXiv  Detail & Related papers  (2023-10-26T17:07:50Z)
• NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages [54.808217147579036]
  We conduct a case study on Indonesian local languages. We compare the effectiveness of online scraping, human translation, and paragraph writing by native speakers in constructing datasets. Our findings demonstrate that datasets generated through paragraph writing by native speakers exhibit superior quality in terms of lexical diversity and cultural content.
  arXiv  Detail & Related papers  (2023-09-19T14:42:33Z)
• Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis [44.17106903728264]
  Most hate speech datasets neglect the cultural diversity within a single language. To address this, we introduce CREHate, a CRoss-cultural English Hate speech dataset. Only 56.2% of the posts in CREHate achieve consensus among all countries, with the highest pairwise label difference rate of 26%.
  arXiv  Detail & Related papers  (2023-08-31T13:14:47Z)
• Multi-lingual and Multi-cultural Figurative Language Understanding [69.47641938200817]
  Figurative language permeates human communication, but is relatively understudied in NLP. We create a dataset for seven diverse languages associated with a variety of cultures: Hindi, Indonesian, Javanese, Kannada, Sundanese, Swahili and Yoruba. Our dataset reveals that each language relies on cultural and regional concepts for figurative expressions, with the highest overlap between languages originating from the same region. All languages exhibit a significant deficiency compared to English, with variations in performance reflecting the availability of pre-training and fine-tuning data.
  arXiv  Detail & Related papers  (2023-05-25T15:30:31Z)
• Comparing Biases and the Impact of Multilingual Training across Multiple Languages [70.84047257764405]
  We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language's culture.
  arXiv  Detail & Related papers  (2023-05-18T18:15:07Z)

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.