EverTutor

Wang, Chengyao; Chu, Wei-Chen; Chen, Hou-Ren; Hsu, Chun‐Yen; Chen, Mike Y.

doi:10.1145/2556288.2557407

Cited by 21 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Humans could provide input, e.g., ToolScape [32] gathers steps from crowdworkers and converges them through clustering algorithms. EverTutor [68] converts smartphone demonstrations by humans into interactive tutorials. Humans could also refine computational results, e.g., VideoWhiz [49] and RecipeDeck [12] both employ Part-of-Speech (POS) tagging to detect cooking actions and objects and then rely on annotators to refine the results.…”

Section: Related Work 21 Mixed-media Tutorialsmentioning

confidence: 99%

“…To explore the design space of cross-domain mixed-media tutorials, we analyzed 13 mixed-media tutorials from three websites [44,71,76] and 10 research papers [12,14,20,32,39,49,53,65,68,74], covering at least five domains including cooking, makeup, vehicle repair, software usage, and educational lectures. Though we focus on tutorials of physical tasks, we also borrow inspiration from other domains, e.g., lectures.…”

Section: Level 1: Components In Mixed-media Tutorialsmentioning

confidence: 99%

“…Figure 2 provides step examples in mixed-media tutorials. Specifically, Figure 2a shows a step in an interactive smartphone tutorial, marked by an overlay indicating the screen area to be clicked [68]; Figure 2b depicts an auto-generated YouTube Chapter for a DIY craft video featuring text, images, and video clips (with timestamps); Figure 2c illustrates a step in a cooking tutorial, where red and blue dots signify ingredients and actions, respectively [12]. Comprehensive details are in the Appendix.…”

Section: Stepmentioning

confidence: 99%

“…In both studies, we used auto-generated YouTube Chapters [54] as the baseline. Although TutoAI was inspired by previous works, these tutorials were either generated automatically using a domainspecific approach [14,20,31,65,68] or manually without AI assistance [39,74]. Mixed-initiative approaches [12,32,49,53] do not provide comparable creation experience like TutoAI.…”

Section: Objectsmentioning

confidence: 99%

See 3 more Smart Citations

TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks

Chen,

Morariu,

Truong

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

Section: Related Work 21 Mixed-media Tutorialsmentioning

confidence: 99%

Section: Level 1: Components In Mixed-media Tutorialsmentioning

confidence: 99%

Section: Stepmentioning

confidence: 99%

Section: Objectsmentioning

confidence: 99%

See 2 more Smart Citations

TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks

Chen,

Morariu,

Truong

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

Training industrial end‐user programmers with interactive tutorials

et al. 2022

View full text Add to dashboard Cite

Newly released robot programming tools have made it feasible for end‐users to program industrial robots by combining block‐based languages and lead‐through programming. To use these systems effectively, end‐users, who usually have limited or no programming experience, require training. To train users, tutoring systems are often used for block‐based programming—some even for lead‐through programming—but no tutorial system combines these two types of programming. We present CoBlox Interactive Tutorials (CITs), a novel tutoring approach that teaches how to use both the hardware and software components that comprise a typical end‐user robot programming environment. As users switch between the two programming styles, CITs provide them with extensive scaffolding, give users immediate feedback on missteps, and provide guidance on next steps. To evaluate CITs, we conducted a study with 79 industrial end‐users using a programming environment released by ABB Robotics that compares our approach to training with training videos, the most commonly used training in industry. This study, one of the largest to date on training professional end‐users, found that CIT‐trained users authored more correct programs in less time than video‐trained users. This shows that a tight integration of hardware and software concepts is crucial to training end‐users to program industrial robots.

show abstract

Understanding the Authoring and Playthrough of Nonvisual Smartphone Tutorials

Rodrigues

Santos

Montague

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Mobile device users are required to constantly learn to use new apps, features, and adapt to updates. For blind people, adapting to a new interface requires additional time and effort. At the limit, and often so, devices and applications may become unusable without support from someone else. Using tutorials is a common approach to foster independent learning of new concepts and workflows. However, most tutorials available online are limited in scope, detail, or quickly become outdated. Also, they presume a degree of tech savviness that is not at the reach of the common mobile device user. Our research explores the democratization of assistance by enabling non-technical people to create tutorials in their mobile phones for others. We report on the interaction and information needs of blind people when following 'amateur' tutorials. Thus, providing insights into how to widen and improve the authoring and playthrough of these learning artifacts. We conducted a study where 12 blind users followed tutorials previously created by blind or sighted people. Our findings suggest that instructions authored by sighted and blind people are limited in different aspects, and that those limitations prevent effective learning of the task at hand. We identified the types of contents produced by authors and the information required by followers during playthrough, which often do not align. We provide insights on how to support both authoring and playthrough of nonvisual smartphone tutorials. There is an opportunity to design solutions that mediate authoring, combine contributions, adapt to user profile, react to context and are living artifacts capable of perpetual improvement.

show abstract

EverTutor

Cited by 21 publications

References 21 publications

TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks

TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks

Training industrial end‐user programmers with interactive tutorials

Understanding the Authoring and Playthrough of Nonvisual Smartphone Tutorials

Contact Info

Product

Resources

About