LaMPost: Design and Evaluation of an AI-assisted Email Writing Prototype for Adults with Dyslexia

  title={LaMPost: Design and Evaluation of an AI-assisted Email Writing Prototype for Adults with Dyslexia},
  author={Steven M. Goodman and Erin Buehler and Patrick Clary and Andy Coenen and Aaron Donsbach and Tiffanie Horne and Michal Lahav and Robert Macdonald and Rain Michaels and Ajit Narayanan and Mahima Pushkarna and Joel Riley and Alex Novaes Santana and Lei Shi and Rachel Sweeney and Phil Weaver and Ann Yuan and Meredith Ringel Morris},
  journal={Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility},
Prior work has explored the writing challenges experienced by people with dyslexia, and the potential for new spelling, grammar, and word retrieval technologies to address these challenges. However, the capabilities for natural language generation demonstrated by the latest class of large language models (LLMs) highlight an opportunity to explore new forms of human-AI writing support tools. In this paper, we introduce LaMPost, a prototype email-writing interface that explores the potential for… 

Figures from this paper

Beyond Safety: Toward a Value-Sensitive Approach to the Design of AI Systems

It is proposed that the AI community should incorporate ideas from the Value-Sensitive Design framework from the Human-Computer Interaction community to ensure the needs and values of all stakeholders are reflected in the systems the authors build.

The Design Space of Generative Models

This work explores what it means to develop an AI model design space by proposing two design spaces relating to generative AI models: the first considers how HCI can impact generative models (i.e., interfaces for models) and the second considers howGenerative models can impact HCI (i., models as an HCI prototyping material).



Design and Evaluation of a Social Media Writing Support Tool for People with Dyslexia

Additional Writing Help (AWH) was designed and implemented - a writing assistance tool to proofread text produced by users with dyslexia before they post on Facebook, powered by a neural machine translation (NMT) model that translates dyslexi style to non-dyslexia style writing.

Wordcraft: Story Writing With Large Language Models

This work built Wordcraft, a text editor in which users collaborate with a generative language model to write a story, and shows that large language models enable novel co-writing experiences.

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

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 reveals benefits for ideation, and costs for efficiency, when suggesting multiple phrases.

Context-Aware Abbreviation Expansion Using Large Language Models

This work proposes a paradigm in which phrases are abbreviated aggressively as primarily word-initial letters, and aims to expand the abbreviations into full-phrase options by leveraging conversation context with the power of pretrained large language models (LLMs).

Understanding the Needs of Searchers with Dyslexia

Differences in behaviors and preferences between dyslexic and non-dyslexic searchers are demonstrated, and it is indicated that factoring readability into search engine rankings and/or interfaces may benefit both dyslexi andnon-d Dyslexic users.

Beyond spelling: the writing skills of students with dyslexia in higher education

To have a clearer idea of the problems students with dyslexia may face during their studies, we compared writings of 100 students with dyslexia and 100 age matched control students in higher

Simplify or help?: text simplification strategies for people with dyslexia

Overall, participants with dyslexia found texts presented with the new strategy significantly more readable and comprehensible.

How a Stylistic, Machine-Generated Thesaurus Impacts a Writer's Process

A machine learning approach to thesaurus generation is presented, using word embeddings, that leverages stylistically distinct corpora -- such as naturalist writing, novels by a particular author, or writing from a technical discipline.

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

To systematically study and benchmark social biases in open-ended language generation, the Bias in Open-Ended Language Generation Dataset (BOLD) is introduced, a large-scale dataset that consists of 23,679 English text generation prompts for bias benchmarking across five domains: profession, gender, race, religion, and political ideology.

Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models

AI-steering tools were developed that increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.