A Design Space for Intelligent and Interactive Writing Assistants

Welcome to our design space for intelligent and interactive writing assistants! The design space consists of five aspects: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension). Please refer to our paper for the detailed definitions of each dimension and code.

To create this design space, we collaborated with researchers from a variety of disciplines, including Human-Computer Interaction (HCI), Natural Language Processing (NLP), Information Systems, and Education, and annotated 115 papers from HCI and NLP fields to understand the current landscape of writing assistants. We hope that our design space offers researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

Our design space is a living artifact, as it will evolve over time alongside the fields. We invite the community to contribute to this artifact by adding new papers, annotations, and discussions to track future developments in this space. Please visit our GitHub repository and contribute to the artifact.

$The figure shows the integrated design space for writing assistants. It is comprised of five boxes, Ecosystem, Task, User, Interaction, and Technology. \n Ecosystem is the biggest box that surrounds the rest, and has the following items: Digital infrastructure (e.g., usability consistency, technical interoperability), Social factors (e.g., designing with stakeholders, desigining for social writing), Locale (e.g., local writing, remote writing), Access model (e.g., free and/or open-source software, commercial software), Norms and Rules (e.g., laws, conventions), and Change over time (e.g., authors, readers, writing, information environment). \n The top part inside Ecosystem box is occupied by Task box, which overlaps with User, Interaction, and Technology boxes. Task box has the following items: Writing stage (e.g., planning, drafting, revision), Writing context (e.g., academic, journalistic, technical), Purpose (e.g., expository, narrative, descriptive), Specificity (e.g., general direction, detailed requirements), and Audience (e.g., specified, implied).\n Interaction box is positioned in the middle of the User and Technology boxes, with arrows connecting to and from these boxes. Interaction has the following points: User - Steering the system (e.g., explicit, implicit, no control), User - Integrating system output (e.g., selection, inspiration), UI - Interface paradigm (e.g., text editor, chatbot), UI - Layout (e.g., writing area, separated, input UI), UI - Visual differentiation (e.g., formatting, location), UI - Interaction metaphor (e.g., agent, tool, hybrid), UI - Initiation (e.g., user-initiated, system-initiated), Technology - Output type (e.g., analysis, generation), Technology - Curation type (e.g., deterministic, curated options), and Technology - User Data access (e.g., input text, additional data). \n User box is on the left of the Interaction box, with the following points: Demographic profile (e.g., age, language and culture), User capabilities (e.g., writing expertise, efficiency), Relationship to system (e.g., agency, ownership, trust), and System output preferences (e.g., coherence, diversity). \n Technology box is on the left of Interaction box and below the User box, with the following points: Data - Source (e.g., experts, users), Data - Size (e.g., small, medium, large), Model - Type (e.g., rule-based, foundation models), Model - External resource access (e.g., tool, data), Learning - Problem (e.g., classification, generation), Learning - Algorithm (e.g., supervised, unsupervised), Learning - Training and adaptation (e.g., fine-tuning, prompting), Evaluation - Evaluator (e.g., automatic, machine-learned), Evaluation - Focus (e.g., linguistic quality, controllability), and Scalability (e.g., cost, latency).$


0	Recognizing Syntactic Errors in the Writing of Second Language Learners	1998	Revision	Professional	Educational	General Direction	Specified	Language & culture	Language & culture	Writing expertise	Writing expertise	Other, Ownership	Other, Ownership	Textual coherence	Textual coherence	User	Medium (<10k)	Rule-based model	Tool, Data	Structured prediction		Tuning decoding parameters	Automatic evaluation	Linguistic quality	Cost	Tool	Separated	Text editor	Formatting	Analysis	Selection	Explicit	Input text	Deterministic	User-initiated
1	The Role of Centering Theory's Rough-Shift in the Teaching and Evaluation of Writing Skills	2000	Drafting, Revision	Academic	Educational	General Direction	Specified	Education	Profession, Education	Writing expertise	Writing expertise	Ownership	Ownership	Textual coherence	Textual coherence												Separated
2	PENS: A Machine-aided English Writing System for Chinese Users	2000	Drafting		Translation	Nonspecific	Implied	Language & culture	Language & culture	Writing expertise		Ownership		Textual coherence	Textual coherence	Machine	Large (<1M)	Statistical ML model	Data	Generation	Supervised learning	Fine-tuning	Automatic evaluation	Linguistic quality	Cost	Tool	Writing area	Text editor	Formatting	Proposal, Generation	Selection	Explicit	Input text	Curated options	User-initiated
3	A Writer's Collaborative Assistant	2002	Planning	Academic	Educational	Specific Objectives	Specified	Profession	Profession, Education	Efficiency	Technical proficiency	Agency	Agency			Machine		Rule-based model	Data	Structured prediction	Supervised learning	Other	Human evaluation		Cost	Tool	Writing area	Text editor	Location	Generation	Inspiration	No control	Input text	Curated options	System-initiated	Technical interoperability, Usability consistency	Free and open-source software	Designing for social writing	Local writing		Writing
4	Toward Evaluation of Writing Style: Overly Repetitious Word Use	2003						Education	Profession	Writing expertise	Writing expertise	Ownership	Ownership	Textual diversity	Textual diversity	Expert	Medium (<10k)	Deep neural network		Classification	Supervised learning	Fine-tuning	Automatic evaluation	Linguistic quality	Cost
5	Automatic Analysis of Plot for Story Rewriting	2004	Revision	Creative	Educational	Specific Objectives	Specified									Expert	Medium (<10k)	Statistical ML model		Structured prediction	Supervised learning	Training from scratch	Automatic evaluation	Linguistic quality	Cost
6	Automated Japanese Essay Scoring System based on Articles Written by Experts	2006																								Tool	Separated	Other	Location	Analysis	No integration	Explicit	Input text	Deterministic	User-initiated
7	Is the Sky Pure Today? AwkChecker: An Assistive Tool for Detecting and Correcting Collocation Errors	2008	Revision	Academic	Educational	General Direction	Implied	Language & culture	Language & culture	Writing expertise, Cognition	Writing expertise, Confidence	Transparency, Agency	Transparency	Textual coherence, Explainability	Explainability	Other	Unknown	Rule-based model	Data	Classification, Generation	Unsupervised learning		Human evaluation	Linguistic quality		Tool	Separated	Text editor	Location	Proposal, Generation	Inspiration, Selection	Explicit	Input text	Model	User-initiated, System-initiated	Usability consistency	Free and open-source software	Designing with stakeholders		Conventions	Writing
8	Common Sense Assistant for Writing Stories That Teach Social Skills	2008	Drafting	Creative	Accessibility	General Direction	Specified			Empathy	Creativity			Textual coherence, Textual diversity	Textual coherence, Textual diversity		Unknown	Rule-based model		Generation			Human evaluation	Style & adequacy		Hybrid, Tool	Separated	Text editor	Location	Proposal	Inspiration	No control	Input text	Model	System-initiated, User-initiated			Designing with stakeholders		Conventions	Readers, Writing
9	RiTa: Creativity Support for Computational Literature	2009	Drafting	Creative	Educational	Nonspecific		Profession, Education	Education	Cognition, Creativity, Efficiency	Creativity, Confidence, Cognition	Transparency																								Technical interoperability	Free and open-source software	Designing with stakeholders			Writing

A Design Space for Intelligent and Interactive Writing Assistants

Annotated Papers