Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Conversation Progress Guide : UI System for Enhancing Self-Efficacy in Conversational AI

Daeun Jeong, Sungbok Shin, Jongwook Jeong

TL;DR

The paper tackles the problem that generative conversational AI can reduce user self-efficacy due to failures and opaque progress in multi-turn tasks. It introduces the Conversation Progress Guide (CPG), a two-agent UI that visually tracks and displays subtasks via a Progress Bar and Subtask Markers, aiming to evoke mastery experiences without changing the underlying AI. A user study (n=22) shows that CPG significantly enhances task-specific self-efficacy compared to a baseline interface, while cognitive load, satisfaction, task time, and interaction counts remain unaffected. The work provides a design framework and empirical evidence for progress-based feedback in goal-oriented dialogue systems, with implications for education and applications where sustained user engagement is critical.

Abstract

In this study, we introduce the Conversation Progress Guide (CPG), a system designed for text-based conversational AI interactions that provides a visual interface to represent progress. Users often encounter failures when interacting with conversational AI, which can negatively affect their self-efficacy-an individual's belief in their capabilities, reducing their willingness to engage with these services. The CPG offers visual feedback on task progress, providing users with mastery experiences, a key source of self-efficacy. To evaluate the system's effectiveness, we conducted a user study assessing how the integration of the CPG influences user engagement and self-efficacy. Results demonstrate that users interacting with a conversational AI enhanced by the CPG showed significant improvements in self-efficacy measures compared to those using a conventional conversational AI.

Conversation Progress Guide : UI System for Enhancing Self-Efficacy in Conversational AI

TL;DR

The paper tackles the problem that generative conversational AI can reduce user self-efficacy due to failures and opaque progress in multi-turn tasks. It introduces the Conversation Progress Guide (CPG), a two-agent UI that visually tracks and displays subtasks via a Progress Bar and Subtask Markers, aiming to evoke mastery experiences without changing the underlying AI. A user study (n=22) shows that CPG significantly enhances task-specific self-efficacy compared to a baseline interface, while cognitive load, satisfaction, task time, and interaction counts remain unaffected. The work provides a design framework and empirical evidence for progress-based feedback in goal-oriented dialogue systems, with implications for education and applications where sustained user engagement is critical.

Abstract

In this study, we introduce the Conversation Progress Guide (CPG), a system designed for text-based conversational AI interactions that provides a visual interface to represent progress. Users often encounter failures when interacting with conversational AI, which can negatively affect their self-efficacy-an individual's belief in their capabilities, reducing their willingness to engage with these services. The CPG offers visual feedback on task progress, providing users with mastery experiences, a key source of self-efficacy. To evaluate the system's effectiveness, we conducted a user study assessing how the integration of the CPG influences user engagement and self-efficacy. Results demonstrate that users interacting with a conversational AI enhanced by the CPG showed significant improvements in self-efficacy measures compared to those using a conventional conversational AI.
Paper Structure (32 sections, 9 figures, 5 tables)

This paper contains 32 sections, 9 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Self-Efficacy
  4. Interfaces that Enhance Self-Efficacy
  5. Failures on Generative Conversational AI
  6. Solution Approach
  7. Design Requirements
  8. Conversation Progress Guide Architecture
  9. User Interface
  10. Progress Bar
  11. Subtask Marker
  12. User Study and Results
  13. User study
  14. Task and System Implementation
  15. Task
  16. ...and 17 more sections

Figures (9)

  • Figure 1: The system architecture of the CPG, highlighting the interaction between the Task Agent and the Progress Feedback Agent in providing feedback to users.
  • Figure 2: User Interface of Conversation Progress Guide
  • Figure 3: The task instruction for user study.
  • Figure 4: Evaluation rules for the “Multiplication of Primes” subtask, as used by the Progress Feedback Agent to assess completion.
  • Figure 5: Average scores of Pre- and Post-Self-Efficacy Survey for the control group. Error bars represent standard deviations.
  • ...and 4 more figures