arXiv subjects

Barbara Kitchenham

Publications and source records attributed to Barbara Kitchenham.

4 recordsLinked to original sources

arXiv2026

Preliminary Guidelines for Using and Evaluating GenAI Tools to Support Systematic Literature Reviews

Context: Generative AI (GenAI) and Large Language Models (LLMs) are increasingly used for academic tasks in software engineering and beyond, including systematic literature reviews (SLRs). However, while capable of summarizing text, there is no guarantee they can meet the rigour, reliability, and transparency that SLRs require. Objectives: To support researchers intending to conduct SLRs using GenAI or those conducting empirical studies evaluating how well GenAI supports SLR tasks. Methods: First, we conducted a rapid review to identify studies that propose guidelines for evaluating and using GenAI and LLMs to support SLRs. Second, we drew on thought experiments, relevant guidance from the literature, and our own experience conducting SLRs and evaluating tools to develop recommendations for how to use and assess GenAI in the context of SLRs. Results: We discuss the problems researchers face when evaluating GenAI for SLRs. We identify and explain process issues to consider when planning, conducting, and reporting both SLRs using GenAI and evaluations of GenAI tools. Finally, we summarize our results as a set of process recommendations, which we name GUEST (GenAI Use and Evaluation in SLR Tasks). Conclusion: We argue that GenAI requires human oversight and is not currently capable of unsupervised systematic studies. However, it offers the prospect of cost-effective assistance for some repetitive tasks and for additional validation of some complex tasks. Our GUEST recommendations should help software engineering researchers both to conduct and report trustworthy SLRs using GenAI and to provide rigorous independent evaluation studies.

cs.SE↗

arXiv2025

LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews

Context: Large language models (LLMs) are increasingly used to screen literature for systematic reviews (SRs), but the standard confusion-matrix metrics used to evaluate them can mislead under the imbalanced, cost-asymmetric conditions of screening. Objective: We develop and justify LLM4SCREENLIT-practical recommendations for researchers conducting LLM-screening evaluations and for editors and reviewers assessing such studies-differentiated by study type (retrospective benchmarking vs deployment for a specific SR). Method: Using Delgado-Chaves et al. (2025), an 18-LLM benchmark across three biomedical SRs, as a motivating example, we reviewed 28 additional papers and extracted their reported metrics. We propose a Weighted Matthews Correlation Coefficient (WMCC) that integrates MCC's chance-correction with asymmetric misclassification costs, and validated it on three software-engineering (SE) reanalyses, the largest covering 9 LLMs x 24 SE secondary studies (34,528 articles). Results: Across the 29 papers, only 10% reported MCC, only 24% reported full confusion matrices, and none of the five papers claiming workload savings priced false-negative cost. In the largest SE reanalysis, MCC and WMCC disagree on the best LLM in 55% of evaluable studies; in the most striking 9,695-article SE study, the Accuracy-best LLM loses 63.3% of relevant evidence (Lost Evidence), the MCC-best 43.9%, but the WMCC-best only 5.8%. Sensitivity analysis (median crossover at w~=2.7, all <7) supports w=10 as a conservative default. Conclusions: SR-screening evaluations should prioritize Lost Evidence and use cost-sensitive WMCC alongside MCC for ranking. Reporting must include the full confusion matrix and treat unclassifiable outputs as positives requiring human review. Designs should be leakage-aware, with non-LLM baselines when the study aims to inform SR practice and labels are available.

cs.SE↗

arXiv2022

A longitudinal case study on the effects of an evidence-based software engineering training

Context: Evidence-based software engineering (EBSE) can be an effective resource to bridge the gap between academia and industry by balancing research of practical relevance and academic rigor. To achieve this, it seems necessary to investigate EBSE training and its benefits for the practice. Objective: We sought both to develop an EBSE training course for university students and to investigate what effects it has on the attitudes and behaviors of the trainees. Method: We conducted a longitudinal case study to study our EBSE course and its effects. For this, we collect data at the end of each EBSE course (2017, 2018, and 2019), and in two follow-up surveys (one after 7 months of finishing the last course, and a second after 21 months). Results: Our EBSE courses seem to have taught students adequately and consistently. Half of the respondents to the surveys report making use of the new skills from the course. The most-reported effects in both surveys indicated that EBSE concepts increase awareness of the value of research and evidence and EBSE methods improve information gathering skills. Conclusions: As suggested by research in other areas, training appears to play a key role in the adoption of evidence-based practice. Our results indicate that our training method provides an introduction to EBSE suitable for undergraduates. However, we believe it is necessary to continue investigating EBSE training and its impact on software engineering practice.

cs.SE↗

arXiv2020

Empirical Standards for Software Engineering Research

Empirical Standards are natural-language models of a scientific community's expectations for a specific kind of study (e.g. a questionnaire survey). The ACM SIGSOFT Paper and Peer Review Quality Initiative generated empirical standards for research methods commonly used in software engineering. These living documents, which should be continuously revised to reflect evolving consensus around research best practices, will improve research quality and make peer review more effective, reliable, transparent and fair.

cs.SE↗