Lune

EMNLP Findings2023

Analysis of Style-Shifting on Social Media: Using Neural Language Model Conditioned by Social Meanings

Seiya Kawano, Shota Kanezaki, Angel Fernando Garcia Contreras, Akishige Yuguchi, Marie Katsurai, Koichiro Yoshino

Abstract

In this paper, we propose a novel framework for evaluating style-shifting in social media conversations. Our proposed framework captures changes in an individual's conversational style based on surprisals predicted by a personalized neural language model for individuals. Our personalized language model integrates not only the linguistic contents of conversations but also non-linguistic factors, such as social meanings, including group membership, personal attributes, and individual beliefs. We incorporate these factors directly or implicitly into our model, leveraging large, pre-trained language models and feature vectors derived from a relationship graph on social media. Compared to existing models, our personalized language model demonstrated superior performance in predicting an individual's language in a test set. Furthermore, an analysis of style-shifting utilizing our proposed metric based on our personalized neural language model reveals a correlation between our metric and various conversation factors as well as human evaluation of style-shifting.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment cites Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. When Style Breaks Safety: Defending LLMs Against Superficial Style AlignmentYuxin Xiao, Sana Tonekaboni, Walter Gerych, Vinith Menon Suriyakumar et al.ICLR 2026 · 8 citations

Builds on1

  1. Style is NOT a single variable: Case Studies for Cross-Stylistic Language UnderstandingDongyeop Kang, Eduard H. HovyACL 2021

Related papers

  1. An Empirical Analysis of the Writing Styles of Persona-Assigned LLMsManuj Malik, Jing Jiang, Kian Ming A. ChaiEMNLP 2024 · 2 citations
  2. Leverage Social Media for Personalized Stress DetectionXin Wang, Huijun Zhang, Lei Cao, Ling FengACM MM 2020 · 28 citations
  3. Dynamic Online Conversation RecommendationXingshan Zeng, Jing Li, Lu Wang, Zhiming Mao et al.ACL 2020 · 10 citations
  4. Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer MetricsAmalie Brogaard Pauli, Isabelle Augenstein, Ira AssentEMNLP Findings 2025
  5. Building User-oriented Personalized Machine Translator based on User-Generated Textual ContentPeng Zhang, Zhengqing Guan, Baoxi Liu, Sharon Xianghua Ding et al.CSCW 2022 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines