Searching for Relevant Lessons Learned Using Hybrid Information Retrieval Classifiers: A Case Study in Software Engineering

TL;DR

This paper investigates hybrid information retrieval classifiers to improve searching relevant lessons learned in software engineering, demonstrating that hybrid classifiers outperform individual ones on an industrial dataset.

Contribution

It extends previous work by evaluating hybridization techniques for LL classifiers, showing improved performance in domain-specific search tasks.

Findings

Hybrid classifiers outperform individual classifiers by up to 25%.

Two hybridization techniques from literature were effectively applied.

The approach is validated on an industrial dataset of 212 LL records.

Abstract

The lessons learned (LL) repository is one of the most valuable sources of knowledge for a software organization. It can provide distinctive guidance regarding previous working solutions for historical software management problems, or former success stories to be followed. However, the unstructured format of the LL repository makes it difficult to search using general queries, which are manually inputted by project managers (PMs). For this reason, this repository may often be overlooked despite the valuable information it provides. Since the LL repository targets PMs, the search method should be domain specific rather than generic as in the case of general web searching. In previous work, we provided an automatic information retrieval based LL classifier solution. In our solution, we relied on existing project management artifacts in constructing the search query on-the-fly. In this paper, we extend our previous work by examining the impact of the hybridization of multiple LL classifiers, from our previous study, on performance. We employ two of the hybridization techniques from the literature to construct the hybrid classifiers. An industrial dataset of 212 LL records is used for validation. The results show the superiority of the hybrid classifier over the top achieving individual classifier, which reached 25%.