Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Self-Elicitation of Requirements with Automated GUI Prototyping

Kristian Kolthoff, Christian Bartelt, Simone Paolo Ponzetto, Kurt Schneider

TL;DR

SERGUI tackles early requirements elicitation for user-facing software by enabling customers to self-elicit requirements through automated NL-based GUI prototyping and LLM-assisted feature recommendations. It integrates NL-based GUI retrieval and ranking with a few-shot GPT-4 prompting mechanism to propose GUI features within an iterative interaction model, producing a prototyping artifact. Preliminary evaluation across cross-domain GUIs shows strong feature recommendation (MAP $0.741$, MRR $0.816$) and meaningful GUI reranking improvements, suggesting substantial potential to reduce analyst effort and accelerate stakeholder feedback in the initial RE phase. The work provides a practical pipeline and datasets to support SER-enabled GUI prototyping and sets the stage for broader user studies.

Abstract

Requirements Elicitation (RE) is a crucial activity especially in the early stages of software development. GUI prototyping has widely been adopted as one of the most effective RE techniques for user-facing software systems. However, GUI prototyping requires (i) the availability of experienced requirements analysts, (ii) typically necessitates conducting multiple joint sessions with customers and (iii) creates considerable manual effort. In this work, we propose SERGUI, a novel approach enabling the Self-Elicitation of Requirements (SER) based on an automated GUI prototyping assistant. SERGUI exploits the vast prototyping knowledge embodied in a large-scale GUI repository through Natural Language Requirements (NLR) based GUI retrieval and facilitates fast feedback through GUI prototypes. The GUI retrieval approach is closely integrated with a Large Language Model (LLM) driving the prompting-based recommendation of GUI features for the current GUI prototyping context and thus stimulating the elicitation of additional requirements. We envision SERGUI to be employed in the initial RE phase, creating an initial GUI prototype specification to be used by the analyst as a means for communicating the requirements. To measure the effectiveness of our approach, we conducted a preliminary evaluation. Video presentation of SERGUI at: https://youtu.be/pzAAB9Uht80

Self-Elicitation of Requirements with Automated GUI Prototyping

TL;DR

SERGUI tackles early requirements elicitation for user-facing software by enabling customers to self-elicit requirements through automated NL-based GUI prototyping and LLM-assisted feature recommendations. It integrates NL-based GUI retrieval and ranking with a few-shot GPT-4 prompting mechanism to propose GUI features within an iterative interaction model, producing a prototyping artifact. Preliminary evaluation across cross-domain GUIs shows strong feature recommendation (MAP , MRR ) and meaningful GUI reranking improvements, suggesting substantial potential to reduce analyst effort and accelerate stakeholder feedback in the initial RE phase. The work provides a practical pipeline and datasets to support SER-enabled GUI prototyping and sets the stage for broader user studies.

Abstract

Requirements Elicitation (RE) is a crucial activity especially in the early stages of software development. GUI prototyping has widely been adopted as one of the most effective RE techniques for user-facing software systems. However, GUI prototyping requires (i) the availability of experienced requirements analysts, (ii) typically necessitates conducting multiple joint sessions with customers and (iii) creates considerable manual effort. In this work, we propose SERGUI, a novel approach enabling the Self-Elicitation of Requirements (SER) based on an automated GUI prototyping assistant. SERGUI exploits the vast prototyping knowledge embodied in a large-scale GUI repository through Natural Language Requirements (NLR) based GUI retrieval and facilitates fast feedback through GUI prototypes. The GUI retrieval approach is closely integrated with a Large Language Model (LLM) driving the prompting-based recommendation of GUI features for the current GUI prototyping context and thus stimulating the elicitation of additional requirements. We envision SERGUI to be employed in the initial RE phase, creating an initial GUI prototype specification to be used by the analyst as a means for communicating the requirements. To measure the effectiveness of our approach, we conducted a preliminary evaluation. Video presentation of SERGUI at: https://youtu.be/pzAAB9Uht80
Paper Structure (14 sections, 2 figures)

This paper contains 14 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Approach: SERGUI
  3. Interaction Model
  4. NL-Based GUI Ranking
  5. NL-Based GUI Feature Ranking
  6. LLM-Based GUI Feature Recommendation
  7. Feature-Based GUI Reranking
  8. Prototyping Artifact
  9. Experimental Evaluation
  10. GUI Feature Recommendation Relevance
  11. GUI Feature Ranking Relevance
  12. GUI Reranking Performance
  13. Related Work
  14. Conclusion and Future Work

Figures (2)

  • Figure 1: Overview of the SERGUI approach with (A) the interaction model showing the main interaction mechanisms, (B) NL-based GUI ranking approach, (C) the NL-based GUI feature ranking and (D) the LLM-based GUI feature recommendation
  • Figure 2: Web app implementation of the SERGUI approach with a chat-section, workbench and GUI prototype preview