Cross-lingual syntactic variation over age and gender

By Anders Johannsen, Dirk Hovy, Anders Søgaard. 2015

91 citations recorded by the source corpus.

Most computational sociolinguistics studies have focused on phonological and lexical variation. We present the first large-scale study of syntactic variation among demographic groups (age and gender) across several languages. We harvest data from online user-review sites and parse it with universal dependencies. We show that several age and gender-specific variations hold across languages, for example that women are more likely to use VP conjunctions.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

The Social Impact of Natural Language Processing (2016, background): “People use this signal consciously, to portray themselves in a certain way, but can also be identified as members of specific groups by their use of subconscious traits (Silverstein, 2003; Agha, 2005; Johannsen et al., 2015; Hovy and Johannsen, 2016).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “…of non-canonical language (e.g. Eisenstein, 2013); the impact of social and demographic factors on language use (e.g. Hovy & Søgaard, 2015; Johannsen et al., 2015); the prevalence of paralinguistic features such as affect, irony and humour (Pang & Lee, 2008; Lukin & Walker, 2013); and…”
Challenges of studying and processing dialects in social media (2015, background): “A number of recent papers have explored social media with respect to sociolinguistic and dialectological questions (Rao et al., 2010; Eisenstein, 2013; Volkova et al., 2013; Doyle, 2014; Hovy et al., 2015; Volkova et al., 2015; Johannsen et al., 2015; Hovy and Søgaard, 2015; Eisenstein, to appear).”
Tagging Performance Correlates with Author Age (2015, positive): “These ﬁndings are in line with the results in Johannsen et al. (2015), who showed that entire (delexicalized) dependency structures correlate with age and gender, often across several languages.”
Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing (2019, neutral): “Similar results hold across various languages in Johannsen et al. (2015).”
Darling or Babygirl ? Investigating Stylistic Bias in Sentiment Analysis (2018, background): “In sociolinguistics, the lexical, phonological, syntactic patterns have been shown to vary across social class, ethnicity, gender, and age (Lawton, 1963; Jørgensen et al., 2016; Schler et al., 2006; Johannsen et al., 2015).”
Analyzing Biases in Human Perception of User Age and Gender from Text (2016, background): “…spectrum of textual features, ranging from paraphrase choice (Preot¸iuc-Pietro et al., 2016), emotions (Volkova and Bachrach, 2016), part-of-speech (Johannsen et al., 2015) and abbreviation usage to social network metadata, web trafﬁc (Culotta et al., 2015), apps installed (Seneviratne et al.,…”
Gender Bias in Machine Translation (2021, background): “Although some correspondences between gender and linguistic features hold across cultures and languages (Smith, 2003; Johannsen et al., 2015), it should be kept in mind that they are far from universal7 and should not be intended in a stereotyped and oversimplified”
Five sources of bias in natural language processing (2021, background): “This mismatch was known to affect text domains, but it also applies to socio-demographic domains: people of, say, different age groups are linguistically as diverse as a text from a web blog and a newspaper (Johannsen et al., 2015).”
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition (2020, background): “Demographic variations root in documents, especially in social media data (Volkova et al., 2013; Hovy, 2015; Johannsen et al., 2015).”
Obfuscating Gender in Social Media Writing (2016, background): “…et al., 2014; Burger et al., 2011; Eisenstein et al., 2010; Li et al., 2014; Liu and Ruths, 2013; Pennacchiotti and Popescu, 2013; Rao et al., 2010; Volkova et al., 2015), weblogs (Mukher-jee and Liu, 2010; Schler et al., 2006; Yan and Yan, 2006) and user-review sites (Johannsen et al., 2015).”
Personalized Machine Translation: Preserving Original Author Traits (2016, background): “We provide here a brief summary of research relevant to our work.”
Computational Sociolinguistics: A Survey (2016, background): “They recognize that this is a simplification, but the value placed on quantification for the purpose of identifying causal connections between variables makes the sacrifice of accuracy worth it.”
Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold (2022, background): “While linguistic differences among genders is shared among some languages, genders differ in very different ways between other languages, e.g., Spanish and Swedish (Johannsen et al., 2015).”
CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech (2019, methodology): “based NLP can be used for several tasks, such as characterizing personal linguistic styles (Johannsen et al., 2015; Hovy and Spruit, 2016; van der Goot et al., 2018; DellOrletta and Nissim, 2018), improving text classification (Mandel et al.”
These are not the Stereotypes You are Looking For: Bias and Fairness in Authorial Gender Attribution (2017, background): “For men they include a higher proportion of determiners, numerical quantifiers (Argamon et al., 2009; Johannsen et al., 2015), and overall verbosity (longer sentences and texts; Newman et al.”