Joel Mire
Logo CMU PhD Student

Hi! I'm Joel, a PhD student in the Language Technologies Institute at Carnegie Mellon University, advised by Maarten Sap.

My research spans natural language processing, computational social science, and cultural analytics.

Recent projects include:

  • Modeling social and structural aspects of narrative discourse in social media
  • Evaluating robustness of deep learning models to linguistic variation, such as dialect
  • Examining how people conceptualize language models and negotiate boundaries for acceptable use and personalization

Currently, I'm exploring computational models of textual interpretation, with particular focus on contextual reasoning and variation across individuals and groups.

I have an M.S. in Language Technologies from CMU and a B.S. in Computer Science and English from Duke University, where I was advised by Aarthi Vadde. I also previously worked as a software engineer at Amazon Web Services.

Curriculum Vitae

Education
  • Carnegie Mellon University
    Carnegie Mellon University
    PhD Student in Language and Information Technologies
    8/25 - Present
  • Carnegie Mellon University
    Carnegie Mellon University
    M.S. in Language Technologies
    8/23 - 8/25
  • Duke University
    Duke University
    B.S. in Computer Science and English
    8/16 - 5/20
  • University of Oxford
    University of Oxford
    Visiting Student
    8/18 - 12/18
Experience
  • Amazon Web Services
    Amazon Web Services
    Software Developer Engineer
    I (8/20 - 3/23), II (4/23 - 8/23)
News
2025
I graduated from my M.S. program and am excited to stay at CMU to pursue a PhD!
Aug 30
Selected Publications (view all )
Social Story Frames: Contextual Reasoning about Narrative Intent and Reception
Social Story Frames: Contextual Reasoning about Narrative Intent and Reception

Joel Mire, Maria Antoniak, Steven R. Wilson, Zexin Ma, Achyutarama R. Ganti, Andrew Piper, Maarten Sap

preprint 2025

We propose and apply a conceptual formalism for reasoning about narrative intent and reader response in conversational stories on social media.

Social Story Frames: Contextual Reasoning about Narrative Intent and Reception

Joel Mire, Maria Antoniak, Steven R. Wilson, Zexin Ma, Achyutarama R. Ganti, Andrew Piper, Maarten Sap

preprint 2025

We propose and apply a conceptual formalism for reasoning about narrative intent and reader response in conversational stories on social media.

Rejected Dialects: Biases Against African American Language in Reward Models
Rejected Dialects: Biases Against African American Language in Reward Models

Joel Mire*, Zubin Trivadi Aysola*, Daniel Chechelnitsky, Nicholas Deas, Chrysoula Zerva, Maarten Sap (* equal contribution)

NAACL (Findings) 2025

We introduce a framework for evaluating dialect biases in reward models and conduct a case study showing biases against African American Language texts.

Rejected Dialects: Biases Against African American Language in Reward Models

Joel Mire*, Zubin Trivadi Aysola*, Daniel Chechelnitsky, Nicholas Deas, Chrysoula Zerva, Maarten Sap (* equal contribution)

NAACL (Findings) 2025

We introduce a framework for evaluating dialect biases in reward models and conduct a case study showing biases against African American Language texts.

The Empirical Variability of Narrative Perceptions of Social Media Texts
The Empirical Variability of Narrative Perceptions of Social Media Texts

Joel Mire, Maria Antoniak, Elliott Ash, Andrew Piper, Maarten Sap

EMNLP 2024

We present a dataset and taxonomy of crowd workers' descriptive perceptions of storytelling, analyzing patterns of disagreement among them and across other annotation contexts, including prescriptive labels from researchers and predictions from LLMs.

The Empirical Variability of Narrative Perceptions of Social Media Texts

Joel Mire, Maria Antoniak, Elliott Ash, Andrew Piper, Maarten Sap

EMNLP 2024

We present a dataset and taxonomy of crowd workers' descriptive perceptions of storytelling, analyzing patterns of disagreement among them and across other annotation contexts, including prescriptive labels from researchers and predictions from LLMs.

Where Do People Tell Stories Online? Story Detection Across Online Communities
Where Do People Tell Stories Online? Story Detection Across Online Communities

Maria Antoniak, Joel Mire, Maarten Sap, Elliott Ash, Andrew Piper

ACL 2024

We develop StorySeeker, a toolkit for detecting stories in online conversations, and use it to illuminate distributional characteristics of storytelling across a community-centric social media platform.

Where Do People Tell Stories Online? Story Detection Across Online Communities

Maria Antoniak, Joel Mire, Maarten Sap, Elliott Ash, Andrew Piper

ACL 2024

We develop StorySeeker, a toolkit for detecting stories in online conversations, and use it to illuminate distributional characteristics of storytelling across a community-centric social media platform.

All publications