Logo des Repositoriums
 

KaggleGPT: Prompt-based Recommender System for Efficient Dataset Discovery

dc.contributor.authorBhoyar, Rahul Rajkumar
dc.contributor.authorWang, Xia
dc.contributor.authorDuong-Trung, Nghia
dc.contributor.editorKiesler, Natalie
dc.contributor.editorSchulz, Sandra
dc.date.accessioned2024-10-21T10:40:35Z
dc.date.available2024-10-21T10:40:35Z
dc.date.issued2024
dc.description.abstractSearching appropriate experimental datasets for machine learning projects and reducing the need for one-on-one student-teacher consultations are both challenging. Despite over 50,000 different datasets available across multiple domains on websites like Kaggle, practitioners often need help locating the necessary datasets. Even with the aid of Kaggle’s API and web search functionalities, the search results are not organized meaningfully to a specific context. Recent developments in artificial intelligence (AI) and large language models (LLMs) provide new means of addressing these relevant issues, which were impossible before. This paper introduces KaggleGPT, an LLM- assisted conversational recommender system designed to streamline finding suitable datasets for students’ projects directly from the textual content. The core of KaggleGPT employs a comprehensive approach by integrating profile-based, expert-based, knowledge-based, and multi-criteria-based recommendation engines. Our vision is for educators and students using KaggleGPT to enhance the educational experience and make dataset discovery more efficient and user-friendly.en
dc.identifier.doi10.18420/delfi2024-ws-30
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/45046
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofProceedings of DELFI Workshops 2024
dc.relation.ispartofseriesDELFI
dc.subjectKaggle
dc.subjectRecommender System
dc.subjectPrompt-based Recommendation
dc.subjectLarge Language Models
dc.subjectDataset Discovery.
dc.titleKaggleGPT: Prompt-based Recommender System for Efficient Dataset Discoveryen
dc.typeText/Conference Paper
mci.conference.date09.-11. September 2024
mci.conference.locationFulda
mci.conference.sessiontitleDELFI: Workshop
mci.document.qualitydigidoc
mci.reference.pages207-214

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
01_bhoyar_kaggle.pdf
Größe:
648.92 KB
Format:
Adobe Portable Document Format