From Online User Feedback to Requirements: Evaluating Large Language Models for Classification and Specification Tasks

TL;DR

This study evaluates lightweight large language models for analyzing online user feedback to support requirements engineering, demonstrating moderate success in classification and specification tasks, and providing insights into their capabilities and limitations.

Contribution

It offers the first empirical evaluation of lightweight LLMs on RE tasks, including a replication package and analysis of their effectiveness and constraints.

Findings

LLMs achieved moderate-to-high classification accuracy (F1 ~ 0.47-0.68)

Specification quality was moderately high (mean ~ 3/5)

Provides insights into LLMs' capabilities and limitations for RE tasks

Abstract

[Context and Motivation] Online user feedback provides valuable information to support requirements engineering (RE). However, analyzing online user feedback is challenging due to its large volume and noise. Large language models (LLMs) show strong potential to automate this process and outperform previous techniques. They can also enable new tasks, such as generating requirements specifications. [Question-Problem] Despite their potential, the use of LLMs to analyze user feedback for RE remains underexplored. Existing studies offer limited empirical evidence, lack thorough evaluation, and rarely provide replication packages, undermining validity and reproducibility. [Principal Idea-Results] We evaluate five lightweight open-source LLMs on three RE tasks: user request classification, NFR classification, and requirements specification generation. Classification performance was measured on two feedback datasets, and specification quality via human evaluation. LLMs achieved moderate-to-high classification accuracy (F1 ~ 0.47-0.68) and moderately high specification quality (mean ~ 3/5). [Contributions] We newly explore lightweight LLMs for feedback-driven requirements development. Our contributions are: (i) an empirical evaluation of lightweight LLMs on three RE tasks, (ii) a replication package, and (iii) insights into their capabilities and limitations for RE.