Towards an AI Knowledge Assistant for Context-aware Learning Experiences in Software Capstone Project Development

Simple item page
dc.catalogadorjca
dc.contributor.authorNeyem, Hugo Andres
dc.contributor.authorGonzález, Luis A.
dc.contributor.authorMendoza Rocha, Marcelo Gabriel
dc.contributor.authorSandoval Alcocer, Juan Pablo
dc.contributor.authorCentellas, Leonardo
dc.contributor.authorParedes, Carlos
dc.date.accessioned2024-05-10T20:02:39Z
dc.date.available2024-05-10T20:02:39Z
dc.date.issued2024
dc.description.abstractSoftware assistants have significantly impacted software development for both practitioners and students, particularly in capstone projects. The effectiveness of these tools varies based on their knowledge sources; assistants with localized, domain-specific knowledge may have limitations, while tools like ChatGPT, using broad datasets, might offer recommendations that do not always match the specific objectives of a capstone course. Addressing a gap in current educational technology, this paper introduces an AI Knowledge Assistant specifically designed to overcome the limitations of existing tools by enhancing the quality and relevance of Large Language Models (LLMs). It achieves this through the innovative integration of contextual knowledge from a local “lessons learned” database tailored to the capstone course. We conducted a study with 150 students using the assistant during their capstone course. Integrated into the Kanban project tracking system, the assistant offered recommendations using different strategies: direct searches in the lessons learned database, direct queries to a GPT model, query enrichment with lessons learned before submission to GPT and LLaMa models, and query enhancement with Stack Overflow data before GPT processing. Survey results underscored a strong preference among students for direct LLM queries and those enriched with local repository insights, highlighting the assistant's practical value. Further, our linguistic analysis conclusively demonstrated that texts generated by the LLM closely mirrored the linguistic standards and topical relevance of university course requirements. This alignment not only fosters a deeper understanding of course content but also significantly enhances the material's applicability to real-world scenarios.
dc.fechaingreso.objetodigital2024-05-10
dc.fuente.origenORCID
dc.identifier.doi10.1109/TLT.2024.3396735
dc.identifier.issn2372-0050
dc.identifier.urihttps://doi.org/10.1109/TLT.2024.3396735
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/85551
dc.information.autorucEscuela de Ingeniería; Neyem, Hugo Andres; 0000-0002-5734-722X; 1007638
dc.information.autorucEscuela de Ingeniería; Mendoza Rocha, Marcelo Gabriel; S/I; 1237020
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaIEEE Transactions on Learning Technologies
dc.rightsacceso abierto
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.titleTowards an AI Knowledge Assistant for Context-aware Learning Experiences in Software Capstone Project Development
dc.typeartículo
sipa.codpersvinculados1007638
sipa.codpersvinculados1237020
sipa.trazabilidadORCID;2024-05-06
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
towards.pdf
Size:
3.85 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas