Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RITA: A Tool for Automated Requirements Classification and Specification from Online User Feedback

Manjeshwar Aniruddh Mallya, Alessio Ferrari, Mohammad Amin Zadenoori, Jacek Dąbrowski

TL;DR

RITA tackles the problem of turning abundant online user feedback into actionable software requirements by providing an end-to-end, LLM-powered workflow. It automates classification of user requests and non-functional concerns, and generates natural-language requirements specifications and user stories, all within a GUI and with direct Jira integration. This bridge between research and practice enables feedback-driven RE to be used earlier and more consistently in development workflows. Future work focuses on evaluating real-world usefulness, improving artefact quality, and expanding model options, including potential commercial LLMs.

Abstract

Context and motivation. Online user feedback is a valuable resource for requirements engineering, but its volume and noise make analysis difficult. Existing tools support individual feedback analysis tasks, but their capabilities are rarely integrated into end-to-end support. Problem. The lack of end-to-end integration limits the practical adoption of existing RE tools and makes it difficult to assess their real-world usefulness. Solution. To address this challenge, we present RITA, a tool that integrates lightweight open-source large language models into a unified workflow for feedback-driven RE. RITA supports automated request classification, non-functional requirement identification, and natural-language requirements specification generation from online feedback via a user-friendly interface, and integrates with Jira for seamless transfer of requirements specifications to development tools. Results and conclusions. RITA exploits previously evaluated LLM-based RE techniques to efficiently transform raw user feedback into requirements artefacts, helping bridge the gap between research and practice. A demonstration is available at: https://youtu.be/8meCLpwQWV8.

RITA: A Tool for Automated Requirements Classification and Specification from Online User Feedback

TL;DR

RITA tackles the problem of turning abundant online user feedback into actionable software requirements by providing an end-to-end, LLM-powered workflow. It automates classification of user requests and non-functional concerns, and generates natural-language requirements specifications and user stories, all within a GUI and with direct Jira integration. This bridge between research and practice enables feedback-driven RE to be used earlier and more consistently in development workflows. Future work focuses on evaluating real-world usefulness, improving artefact quality, and expanding model options, including potential commercial LLMs.

Abstract

Context and motivation. Online user feedback is a valuable resource for requirements engineering, but its volume and noise make analysis difficult. Existing tools support individual feedback analysis tasks, but their capabilities are rarely integrated into end-to-end support. Problem. The lack of end-to-end integration limits the practical adoption of existing RE tools and makes it difficult to assess their real-world usefulness. Solution. To address this challenge, we present RITA, a tool that integrates lightweight open-source large language models into a unified workflow for feedback-driven RE. RITA supports automated request classification, non-functional requirement identification, and natural-language requirements specification generation from online feedback via a user-friendly interface, and integrates with Jira for seamless transfer of requirements specifications to development tools. Results and conclusions. RITA exploits previously evaluated LLM-based RE techniques to efficiently transform raw user feedback into requirements artefacts, helping bridge the gap between research and practice. A demonstration is available at: https://youtu.be/8meCLpwQWV8.
Paper Structure (13 sections, 3 figures)

This paper contains 13 sections, 3 figures.

Table of Contents

  1. Introduction
  2. RITA Tool Description
  3. Use Cases
  4. User Flow and Screen Presentation
  5. Overview of the RITA Architecture
  6. Component View
  7. Use Case Realisation
  8. Feedback Classification and Requirements Specification
  9. Jira Integration and Requirements Export
  10. Deployment View
  11. Implementation
  12. Challenges, Next Steps and Evaluation
  13. Conclusion

Figures (3)

  • Figure 1: User Flow and Screen Presentation in RITA Tool and Integrated Jira Project Management Tool.
  • Figure 2: Structural Overview of the RITA Tool. Arrows indicate usage dependencies and point from the invoking component to the component it uses.
  • Figure 3: Sequence Diagram of RITA (Review Classification Workflow)