The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers

2021/01/22 by Daniel Buschek, Martin Zürn, Malin Eiband · 106 citations
Computer Science · Psychology · #Artificial intelligence #Cognitive science #Composition (language) #Computer science #Ideation #Intelligent Tutoring Systems and Adaptive Learning #Linguistics #Natural language processing #Phrase #Psychology #Software Engineering Research #Topic Modeling #Word (group theory) #cs.CL #cs.HC

paper · pdf · doi:10.1145/3411764.3445372

21 pages, 4 figures, ACM CHI 2021

arxiv created 2021/01/22 · arxiv updated 2021/01/25 · openalex publication_date 2021/05/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

We present an in-depth analysis of the impact of multi-word suggestion choices from a neural language model on user behaviour regarding input and text composition in email writing. Our study for the first time compares different numbers of parallel suggestions, and use by native and non-native English writers, to explore a trade-off of “efficiency vs ideation”, emerging from recent literature. We built a text editor prototype with a neural language model (GPT-2), refined in a prestudy with 30 people. In an online study (N=156), people composed emails in four conditions (0/1/3/6 parallel suggestions). Our results reveal (1) benefits for ideation, and costs for efficiency, when suggesting multiple phrases; (2) that non-native speakers benefit more from more suggestions; and (3) further insights into behaviour patterns. We discuss implications for research, the design of interactive suggestion systems, and the vision of supporting writers with AI instead of replacing them.

Citations

• A Cognitive Process Theory of Writing
• Fitting Linear Mixed-Effects Models Using lme4
• Keystroke Logging in Writing Research
• A tutorial on hidden Markov models and selected applications in speech recognition
• Small latin squares, quasigroups, and loops
• Model Cards for Model Reporting
• Release Strategies and the Social Impacts of Language Models
• Transformers: State-of-the-Art Natural Language Processing
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Language Models are Few-Shot Learners
• Aion Framework: Dimensional Emergence of AI Consciousness, Observer-Induced Collapse, and Cosmological Portal Dynamics
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process