MIWA: Mixed-Initiative Web Automation for Better User Control and Confidence
Weihao Chen, Xiaoyu Liu, Jiacheng Zhang, Ian Iong Lam, Zhicheng Huang, Rui Dong, Xinyu Wang, Tianyi Zhang
Abstract
In the era of Big Data, web automation is frequently used by data scientists, domain experts, and programmers to complete time-consuming data collection tasks. However, developing web automation scripts requires familiarity with a programming language and HTML, which remains a key learning barrier for non-expert users. We provide MIWA, a mixed-initiative web automation system that enables users to create web automation scripts by demonstrating what content they want from the targeted websites. Compared to existing web automation tools, MIWA helps users better understand a generated script and build trust in it by (1) providing a step-by-step explanation of the script’s behavior with visual correspondence to the target website, (2) supporting greater autonomy and control over web automation via step-through debugging and fine-grained demonstration refinement, and (3) automatically detecting potential corner cases that are handled improperly by the generated script. We conducted a within-subjects user study with 24 participants and compared MIWA with Rousillon, a state-of-the-art web automation tool. Results showed that, compared to Rousillon, MIWA reduced the task completion time by half while helping participants gain more confidence in the generated script.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Cited by top-tier papers8
- Dango: A Mixed-Initiative Data Wrangling System using Large Language ModelWei-Hao Chen, Weixi Tong, Amanda Case, Tianyi ZhangCHI 2025 · 19 citations
- From Operation to Cognition: Automatic Modeling Cognitive Dependencies from User Demonstrations for GUI Task AutomationYiwen Yin, Yu Mei, Chun Yu, Toby Jia-Jun Li et al.CHI 2025 · 8 citations
- Efficient Bottom-Up Synthesis for Programs with Local VariablesXiang Li, Xiangyu Zhou, Rui Dong, Yihong Zhang et al.POPL 2024 · 7 citations
- Morae: Proactively Pausing UI Agents for User ChoicesYi-Hao Peng, Dingzeyu Li, Jeffrey P. Bigham, Amy PavelUIST 2025 · 4 citations
- Denicek: Computational Substrate for Document-Oriented End-User ProgrammingTomas Petricek, Jonathan EdwardsUIST 2025 · 2 citations
Related papers
- SemanticOn: Specifying Content-Based Semantic Conditions for Web Automation ProgramsKevin Pu, Rainey Fu, Rui Dong, Xinyu Wang et al.UIST 2022 · 16 citations
- WebEvo: taming web application evolution via detecting semantic structure changesFei Shao, Rui Xu, Wasif Arman Haque, Jingwei Xu et al.ISSTA 2021 · 11 citations
- Glider: A Reinforcement Learning Approach to Extract UI Scripts from WebsitesYuanchun Li, Oriana RivaSIGIR 2021 · 11 citations
- DiLogics: Creating Web Automation Programs with Diverse LogicsKevin Pu, Jim Yang, Angel Yuan, Minyi Ma et al.UIST 2023 · 5 citations
- Dual-View Visual Contextualization for Web NavigationJihyung Kil, Chan Hee Song, Boyuan Zheng, Xiang Deng et al.CVPR 2024
