Diffusion of Lexical Change in Social Media
By Jacob Eisenstein, Brendan T. O'Connor, Noah A. Smith, Eric P. Xing. 2012
269 citations recorded by the source corpus.
Computer-mediated communication is driving fundamental changes in the nature of written language. We investigate these changes by statistical analysis of a dataset comprising 107 million Twitter messages (authored by 2.7 million unique user accounts). Using a latent vector autoregressive model to aggregate across thousands of words, we identify high-level patterns in diffusion of linguistic change over the United States. Our model is robust to unpredictable changes in Twitter's sampling rate, and provides a probabilistic characterization of the relationship of macro-scale linguistic influence to a set of demographic and geographic predictors. The results of this analysis offer support for prior arguments that focus on geographical proximity and population size. However, demographic similarity – especially with regard to race – plays an even more central role, as cities with similar racial demographics are far more likely to share linguistic influence. Rather than moving towards a single unified “netspeak” dialect, language evolution in computer-mediated communication reproduces existing fault lines in spoken American English.
Subfields: Cultural Studies, Language and Linguistics, Natural Language Processing, Human-Computer Interaction, Linguistics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cultural Studies
- Daniel Preotiuc-Pietro
- Franciska de Jong
- Noah A. Smith
- Dong Nguyen
- Ari Holtzman
- A. Seza Doğruöz
- Diyi Yang
- Swabha Swayamdipta
In Language and Linguistics
- Michael Lewis
- Daniel Preotiuc-Pietro
- Svitlana Volkova
- Franciska de Jong
- Noah A. Smith
- Dong Nguyen
- Ari Holtzman
- James Y. Zou
In Natural Language Processing
- Yejin Choi
- Noah A. Smith
- Luke S. Zettlemoyer
- Mohit Bansal
- Hannaneh Hajishirzi
- Percy Liang
- Daniel Khashabi
- Ana Marasovic
In Human-Computer Interaction
- Omar Shaikh
- Daniel Preotiuc-Pietro
- Svitlana Volkova
- Franciska de Jong
- Noah A. Smith
- Dong Nguyen
- Lora Aroyo
- A. Seza Doğruöz
In Linguistics
- Noah A. Smith
- Ari Holtzman
- James Y. Zou
- Doug Downey
- Luke S. Zettlemoyer
- Diyi Yang
- Swabha Swayamdipta
- Carolyn Penstein Rosé
Citations in the corpus
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016, background): “Different demographic and geographic groups also use different dialects and word-choices in social media [8].”
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020, background): “A small body of work has attempted to address this question (Lee, 2001; Eisenstein et al., 2014; van der Wees et al., 2015; Plank, 2016; Ruder et al., 2016, among others).”
- What Does it Mean for a Language Model to Preserve Privacy? (2022, background): “Yet, changes in language can be swift, in particular on social media [82, 29] where movements, such as #MeToo or Black Lives Matter, can quickly and radically shift the meaning of words and phrases.”
- DEMix Layers: Disentangling Domains for Modular Language Modeling (2021, background): “While a growing body of work has attempted to address the structure and composition of language 2http://github.com/kernelmachine/demix domains (Eisenstein et al., 2014; Plank, 2016; Aharoni and Goldberg, 2020; Gururangan et al., 2020), fundamentally what a domain is remains a matter of debate.”
- Computational Sociolinguistics: A Survey (2016, methodology): “[70] studied lexical change in social media by using census data to obtain demographic information of the geographical locations.”
- Can Large Language Models Transform Computational Social Science? (2023, background): “, 2007), both on the internet (Eisenstein, 2012; Eisenstein et al., 2014) and in historical archives (Mihalcea and Nastase, 2012; Kim et al.”
- Semantic Variation in Online Communities of Practice (2018, unknown): “Meaning variation determined by geographical location — including that of Bamman et al. (2014) — has often focused on dialectal varieties in the USA using data from Twitter (Eisenstein et al., Doyle, 2014; Eisenstein et al., 2014).”
- Time Waits for No One! Analysis and Challenges of Temporal Misalignment (2021, background): “This observation is consistent with past work on language change in social media (Stew-art and Eisenstein, 2018; Eisenstein et al., 2014).”
- Studying User Income through Language, Behaviour and Affect in Social Media (2015, background): “Automatic analysis of that content can unveil interesting patterns of language [4] and infer characteristics of users.”
- Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection (2022, background): “Language on the Internet has been historically treated as a noisy variant of English, even though lexical variation on the Internet is highly communicative of social signals (Eisenstein, 2013) and varies considerably along demographic variables (Eisenstein et al., 2014) and community membership (Luc”
- Crowdsourcing Subjective Tasks: The Case Study of Understanding Toxicity in Online Discussions (2019, background): “Evolution of language online can be observed by studying social media data [22].”