From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media

2026-02-13 · Source: Computation and Language · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, quick

Summary

A study analyzed the factors correlating with neology, or new word emergence, in both published writing and social media. Building on prior work that used historical published texts, this research extended the methodology to include contextual embeddings alongside static ones. The analysis applied these techniques to a new corpus of Twitter posts. The findings indicate that the same factors identified in published texts also correlate with neology on Twitter. However, the study suggests that the topic popularity growth factor might contribute less to new word creation on Twitter compared to its influence in published writing. Researchers hypothesize this difference stems from the two domains favoring distinct neologism formation mechanisms.

Key takeaway

For computational linguists studying language evolution, this research highlights that while core neology correlates persist across domains, the specific drivers like topic popularity can differ. You should consider domain-specific mechanisms when modeling word emergence, especially when comparing formal published texts with dynamic social media content, to refine predictive models of linguistic change.

Key insights

Neology correlates similarly across published writing and social media, though topic popularity's influence varies.

Principles

• Language evolution is shaped by contextual pressures.
• Distributional semantics can identify neology factors.

Method

The study extended prior distributional semantic methodology by incorporating contextual embeddings with static ones, applying this to a new corpus of Twitter posts to analyze neology correlates.

In practice

• Analyze language evolution across diverse platforms.
• Compare neologism formation mechanisms by domain.

Topics

• Neology
• Distributional Semantics
• Contextual Embeddings
• Social Media Analysis
• Language Evolution

Best for: AI Scientist, AI Researcher, Research Scientist, AI Student

Related on AIssential

• Semantic Chunking and the Entropy of Natural Language — A new statistical model explains natural language redundancy through hierarchical semantic chunking and predicts variable entropy rates.
• Evolution of Linguistic Patterns in Scientific Writing in Portuguese: An Analysis with NILC-Metrix — Scientific writing in Portuguese abstracts evolved significantly from 2023, showing simplification and increased lexical density.
• Agent-based models for the evolution of morphological alternation patterns — Agent-based simulations, evaluated by an LLM-driven "AI Historical Linguist," model the emergence and spread of morphological alternations in language.
• A corpus-assisted metaphor analysis in portraying businesswomen: Diachronic changes in Hong Kong English news — Corpus-assisted metaphor analysis reveals diachronic shifts in media portrayals of businesswomen.
• From Comments to Trends: Studi NLP dan Computational Linguistics dalam Mendeteksi Topik Viral dari… — NLP and computational linguistics are crucial for detecting social media trends from vast, informal, and diverse comment data.
• Most Influential NAACL Papers (2025-09 Version) — Citation-based rankings reveal evolving research priorities and enduring impact within NLP.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computation and Language.