Oscar Díaz

Oscar Díaz, Xabier Garmendia, Juanan Pereira

The increasing volume of research paper submissions poses a significant challenge to the traditional academic peer-review system, leading to an overwhelming workload for reviewers. This study explores the potential of integrating Large Language Models (LLMs) into the peer-review process to enhance efficiency without compromising effectiveness. We focus on manuscript annotations, particularly excerpt highlights, as a potential area for AI-human collaboration. While LLMs excel in certain tasks like aspect coverage and informativeness, they often lack high-level analysis and critical thinking, making them unsuitable for replacing human reviewers entirely. Our approach involves using LLMs to assist with specific aspects of the review process. This paper introduces AnnotateGPT, a platform that utilizes GPT-4 for manuscript review, aiming to improve reviewers' comprehension and focus. We evaluate AnnotateGPT using a Technology Acceptance Model (TAM) questionnaire with nine participants and generalize the findings. Our work highlights annotation as a viable middle ground for AI-human collaboration in academic review, offering insights into integrating LLMs into the review process and tuning traditional annotation tools for LLM incorporation.

Maider Azanza, Arantza Irastorza, Raul Medeiros et al.

With a volatile labour and technological market, onboarding is becoming increasingly important. The process of incorporating a new developer, a.k.a. the newcomer, into a software development team is reckoned to be lengthy, frustrating and expensive. Newcomers face personal, interpersonal, process and technical barriers during their incorporation, which, in turn, affects the overall productivity of the whole team. This problem exacerbates for Software Product Lines (SPLs), where their size and variability combine to make onboarding even more challenging, even more so for developers that are transferred from the Application Engineering team into the Domain Engineering team, who will be our target newcomers. This work presents concept maps on the role of sensemaking scaffolds to help to introduce these newcomers into the SPL domain. Concept maps, used as knowledge visualisation tools, have been proven to be helpful for meaningful learning. Our main insight is to capture concepts of the SPL domain and their interrelationships in a concept map, and then, present them incrementally, helping newcomers grasp the SPL and aiding them in exploring it in a guided manner while avoiding information overload. This work's contributions are four-fold. First, concept maps are proposed as a representation to introduce newcomers into the SPL domain. Second, concept maps are presented as the means for a guided exploration of the SPL core assets. Third, a feature-driven concept map construction process is introduced. Last, the usefulness of concept maps as guides for SPL onboarding is tested through a formative evaluation. Link to the online demo: url="https://rebrand.ly/wacline-cmap"