Socioeconomic status (SES) structures social inequality and underlies class-based discrimination that is often rationalised through stereotypes expressed in public discourse. However, despite extensive research on hate speech detection in Natural Language Processing, classism detection remains an underexplored phenomenon. We introduce ACID, a cross-cultural corpus with over 1.15 million instances, to investigate classism across YouTube and Twitter from 14 English-speaking countries. We examine (i) which stereotypes are invoked towards lower-SES, (ii) whether blame for lower-SES is attributed to individuals or structural factors, and (iii) whether these people are portrayed offensively. Across platforms, explanations are predominantly framed in terms of individual responsibility. Across countries, class stereotypes consistently revolve around moralized notions of dependency, laziness, and ignorance, revealing a shared global structure of class-based stigma. Our dataset and analysis are a foundation to advance research on class-based discrimination and its representation in online discourse.

Personalized content moderation can protect users from harm while facilitating free expression by tailoring moderation decisions to individual preferences rather than enforcing universal rules.However, content moderation that is fully personalized to individual preferences, no matter what these preferences are, may lead to even the most hazardous types of content being propagated on social media.In this paper, we explore this risk using hate speech as a case study.Certain types of hate speech are illegal in many countries.We show that, while fully personalized hate speech detection models increase overall user welfare (as measured by user-level classification performance), they also make predictions that violate such legal hate speech boundaries, especially when tailored to users who tolerate highly hateful content.To address this problem, we enforce legal boundaries in personalized hate speech detection by overriding predictions from personalized models with those from a boundary classifier.This approach significantly reduces legal violations while minimally affecting overall user welfare.Our findings highlight both the promise and the risks of personalized moderation, and offer a practical solution to balance user preferences with legal and ethical obligations.

Stories play a pivotal role in human communication, shaping beliefs and morals, particularly in children.As parents increasingly rely on large language models (LLMs) to craft bedtime stories, the presence of cultural and gender stereotypes in these narratives raises significant concerns.To address this issue, we present Biased Tales, a comprehensive dataset designed to analyze how biases influence protagonists' attributes and story elements in LLM-generated stories.Our analysis uncovers striking disparities.When the protagonist is described as a girl (as compared to a boy), appearance-related attributes increase by 55.26%.Stories featuring non-Western children disproportionately emphasize cultural heritage, tradition, and family themes far more than those for Western children.Our findings highlight the role of sociocultural bias in making creative AI use more equitable and diverse.

This paper introduces the concept of actionability in the context of bias measures in natural language processing (NLP).We define actionability as the degree to which a measurement's results enable informed action and propose a set of desiderata for assessing it.Building on existing frameworks such as measurement modeling, we argue that actionability is a crucial aspect of bias measures that has been largely overlooked in the literature.We conduct a comprehensive review of 146 papers proposing bias measures in NLP, examining whether and how they provide the information required for actionable results.Our findings reveal that many key elements of actionability, including a measure's intended use and reliability assessment, are often unclear or absent.This study highlights a significant gap in the current approach to developing and reporting bias measures in NLP.We argue that this lack of clarity may impede the effective implementation and utilization of these measures.To address this issue, we offer recommendations for more comprehensive and actionable metric development and reporting practices in NLP bias research.

As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP.Exclusion is particularly harmful in one of the most popular NLP applications, machine translation (MT).Wrong pronoun translations can discriminate against marginalized groups, e.g., non-binary individuals (Dev et al., 2021).In this "reality check", we study how three commercial MT systems translate 3rd-person pronouns.Concretely, we compare the translations of gendered vs. gender-neutral pronouns from English to five other languages (Danish, Farsi, French, German, Italian), and vice versa, from Danish to English.Our error analysis shows that the presence of a gender-neutral pronoun often leads to grammatical and semantic translation errors.Similarly, gender neutrality is often not preserved.By surveying the opinions of affected native speakers from diverse languages, we provide recommendations to address the issue in future MT research.

Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case.However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind.In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices.In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it.Concretely, we compute established gender bias metrics on the WinoMT corpus from English to German and Spanish.We discover that IFT models default to male-inflected translations, even disregarding female occupational stereotypes.Next, using interpretability methods, we unveil that models systematically overlook the pronoun indicating the gender of a target occupation in misgendered translations.Finally, based on this finding, we propose an easy-to-implement and effective bias mitigation solution based on fewshot learning that leads to significantly fairer translations.1

Hate speech is a global phenomenon, but most hate speech datasets so far focus on Englishlanguage content.This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions across the world.More data is needed, but annotating hateful content is expensive, timeconsuming and potentially harmful to annotators.To mitigate these issues, we explore dataefficient strategies for expanding hate speech detection into under-resourced languages.In a series of experiments with mono-and multilingual models across five non-English languages, we find that 1) a small amount of target-language fine-tuning data is needed to achieve strong performance, 2) the benefits of using more such data decrease exponentially, and 3) initial fine-tuning on readily-available English data can partially substitute targetlanguage data and improve model generalisability.Based on these findings, we formulate actionable recommendations for hate speech detection in low-resource language settings.

Federico Bianchi, Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Language models have revolutionized the field of NLP.However, language models capture and proliferate hurtful stereotypes, especially in text generation.Our results show that 4.3% of the time, language models complete a sentence with a hurtful word.These cases are not random, but follow language and genderspecific patterns.We propose a score to measure hurtful sentence completions in language models (HONEST).It uses a systematic template-and lexicon-based bias evaluation methodology for six languages.Our findings suggest that these models replicate and amplify deep-seated societal stereotypes about gender roles.Sentence completions refer to sexual promiscuity when the target is female in 9% of the time, and in 4% to homosexuality when the target is male.The results raise questions about the use of these models in production settings.

During the last years, the phenomenon of hate against women increased exponentially especially in online environments such as microblogs. Although this alarming phenomenon has triggered many studies both from computational linguistic and machine learning points of view, less effort has been spent to analyze if those misogyny detection models are affected by an unintended bias. This can lead the models to associate unreasonably high misogynous scores to a non-misogynous text only because it contains certain terms, called identity terms. This work is the first attempt to address the problem of measuring and mitigating unintended bias in machine learning models trained for the misogyny detection task. We propose a novel synthetic test set that can be used as evaluation framework for measuring the unintended bias and different mitigation strategies specific for this task. Moreover, we provide a misogyny detection model that demonstrate to obtain the best classification performance in the state-of-the-art. Experimental results on recently introduced bias metrics confirm the ability of the bias mitigation treatment to reduce the unintended bias of the proposed misogyny detection model.

Sentiment Analysis is a broad task that involves the analysis of various aspect of the natural language text.However, most of the approaches in the state of the art usually investigate independently each aspect, i.e.Subjectivity Classification, Sentiment Polarity Classification, Emotion Recognition, Irony Detection.In this paper we present a Multi-View Sentiment Corpus (MVSC), which comprises 3000 English microblog posts related the movie domain.Three independent annotators manually labelled MVSC, following a broad annotation schema about different aspects that can be grasped from natural language text coming from social networks.The contribution is therefore a corpus that comprises five different views for each message, i.e. subjective/objective, sentiment polarity, implicit/explicit, irony, emotion.In order to allow a more detailed investigation on the human labelling behaviour, we provide the annotations of each human annotator involved.

Real world applications of machine learning in natural language processing can span many different domains and usually require a huge effort for the annotation of domain specific training data. For this reason, domain adaptation techniques have gained a lot of attention in the last years. In order to derive an effective domain adaptation, a good feature representation across domains is crucial as well as the generalisation ability of the predictive model. In this paper we address the problem of domain adaptation for sentiment classification by combining deep learning, for acquiring a cross-domain high-level feature representation, and ensemble methods, for reducing the cross-domain generalization error. The proposed adaptation framework has been evaluated on a benchmark dataset composed of reviews of four different Amazon category of products, significantly outperforming the state of the art methods.