Synthia: Visually Interpreting and Synthesizing Feedback for Writing Revision
Chao Zhang, Kexin Ju, Zhuolun Han, Yu-Chun Grace Yen, Jeffrey M. Rzeszotarski
Abstract
Figure 1: This figure illustrates how SyntHia supports users in managing, interpreting, and synthesizing feedback for writing revisions. SyntHia decomposes large collections of feedback into interactive, configurable bubbles (A.1), allowing users to adjust visual encodings, such as clustering, color, size, and reflection arcs, to identify patterns and assess feedback helpfulness (A.2 & A.3). Bidirectional highlighting connects feedback to its original context (B.1), similar feedback units (B.2), and the relevant sentences in the text (B.3), helping users understand its meaning, relevance, and impact. Finally, SyntHia facilitates revision by enabling users to synthesize feedback into new drafts (C.1) and track revision versions (C.2), providing a non-linear, traceable interface for exploring alternative edits.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d572b763-a236-41b0-b561-df23e76f55a0Cited by top-tier papers1
Ask how each one uses itBuilds on29
- AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model PromptsTongshuang Wu, Michael Terry, Carrie Jun CaiCHI 2022 · 465 citations
- CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model CapabilitiesMina Lee, Percy Liang, Qian YangCHI 2022 · 340 citations
- Co-Writing with Opinionated Language Models Affects Users' ViewsMaurice Jakesch, Advait Bhat, Daniel Buschek, Lior Zalmanson et al.CHI 2023 · 249 citations
- TaleBrush: Sketching Stories with Generative Pretrained Language ModelsJohn Joon Young Chung, Wooseok Kim, Kang Min Yoo, Hwaran Lee et al.CHI 2022 · 202 citations
- Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language ModelsSangho Suh, Bryan Min, Srishti Palani, Haijun XiaUIST 2023 · 147 citations
Related papers
- Friction: Deciphering Writing Feedback into Writing Revisions through LLM-Assisted ReflectionChao Zhang, Kexin Ju, Peter Bidoshi, Yu-Chun Grace Yen et al.CHI 2025 · 25 citations
- Decipher: An Interactive Visualization Tool for Interpreting Unstructured Design Feedback from Multiple ProvidersYu-Chun (Grace) Yen, Joy O. Kim, Brian P. BaileyCHI 2020 · 27 citations
- Effective Interfaces for Student-Driven Revision Sessions for Argumentative WritingTazin Afrin, Omid Kashefi, Christopher Olshefski, Diane J. Litman et al.CHI 2021 · 30 citations
- Synergi: A Mixed-Initiative System for Scholarly Synthesis and SensemakingHyeonsu B. Kang, Tongshuang Wu, Joseph Chee Chang, Aniket KitturUIST 2023 · 45 citations
- SYNTHIA: Novel Concept Design with Affordance CompositionHyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim, Jiateng Liu et al.ACL 2025
