Lost in Translation: Understanding Autistic–Neurotypical Communication Style Differences in Job Postings

Cognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Participatory DesignUser Research Methods (Interviews, Surveys, Observation)Prototyping & User TestingSpecial Education TeachersFamily CaregiversHCI Researchers

Paper Title

Lost in Translation: Understanding Autistic–Neurotypical Communication Style Differences in Job Postings

Publication Info

  • Topic area: Autistic–neurotypical communication differences in employment contexts
  • Keywords: Autism, neurotypical communication, job postings, interpretive gaps, annotation tools, pragmatic language, accommodations, employment barriers, AI design, accessibility

Background and Problem

  • Problem / challenge: Autistic adults face significant communication barriers in employment contexts, particularly in interpreting job postings written for neurotypical audiences. Prior work has not systematically documented when and why these interpretive gaps occur.
  • Significance: Autistic adults experience unemployment rates of approximately 85%, compared to 4% in the general population. Addressing communication mismatches in job postings could reduce barriers and improve vocational outcomes.
  • Motivation and related work: Previous studies have explored autistic communication traits, anxiety in social contexts, literal interpretation tendencies, and AI-assisted interventions. However, no research has focused on identifying specific language patterns in job postings that lead to interpretive gaps or the reasons behind these challenges.

Solution

  • Proposed approach: ANCAT (Autistic–NT Communication Annotation Tool), a structured annotation interface for capturing interpretive gaps in job postings as perceived by autistic adults.
  • Novelty:
    1. First-of-its-kind dataset documenting autistic–NT communication differences in employment contexts.
    2. Development of ANCAT, an open-source tool for annotating interpretive gaps in text.
    3. Empirical findings characterizing common language challenges in job postings.
    4. Design implications for improving autistic–NT communication and accessibility.
  • Procedure and key techniques:
    • Recruitment of 20 autistic adults to annotate 10 job postings each, using six predefined categories: Unclear, Ambiguous, Incomplete, Inappropriate, Negative, and Other.
    • Follow-up interviews to explore participants’ navigation strategies, rationales, and suggestions for future tools.
    • Qualitative coding and thematic analysis to identify patterns and themes in interpretive gaps.

Results

  • Concrete findings:
    • 683 annotations across 200 job postings, categorized as Unclear (35.1%), Incomplete (16.6%), Ambiguous (15%), Negative (12.4%), Inappropriate (7.9%), and Other (12.9%).
    • Major barriers included vague or implicit social expectations, unmeasurable qualifications, missing details, and exclusionary language.
  • Advantage over baselines:
    • Provides empirical evidence of specific autistic–NT communication mismatches, filling gaps in prior research.
    • Offers actionable insights for designing clearer job postings and supportive technologies.
  • Experiments / evaluation:
    • Annotation dataset analyzed descriptively; interviews coded iteratively to identify themes.
    • Participants described mixed views on LLMs, favoring simpler tools and external verification strategies.
  • Limitations and future work:
    • Small sample size (N = 20) limited to DSM-5 Level 1 autistic adults in the U.S.
    • No neurotypical comparison group; findings may not generalize to higher-support autistic individuals or other cultural contexts.
    • Future work should explore other employment stages, cross-cultural applicability, and intersectional factors such as race and gender.

Summary

This study investigates autistic–neurotypical communication style differences in job postings, identifying interpretive gaps through a novel annotation tool, ANCAT. Findings reveal that implicit social expectations, vague qualifications, and exclusionary language are major barriers for autistic job seekers. The authors provide actionable guidelines for employers and propose design directions for AI systems to improve autistic–NT communication. By releasing the first dataset of its kind, this work lays the foundation for future research and tools to enhance employment equity for autistic individuals.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/chi/222268/2026

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://doi.org/10.1145/3772318.3791853
At a Glance

Paper Snapshot

fact_check
dataset
Source
CHI
calendar_month
Year
2026
emoji_events
Award
No award tagged
group
Authors
6 authors
sell
Subtopics
Cognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia), Participatory Design, User Research Methods (Interviews, Surveys, Observation), Prototyping & User Testing
work
Professions
Special Education Teachers, Family Caregivers, HCI Researchers
article
Content Status
Full text indexed
hub
Related Papers
0 related papers