Inproceedings3917: Unterschied zwischen den Versionen
He9318 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Färber |ErsterAutorVorname=Michael }} {{Publikation Author |Rank=2 |Author=Ann-Kathrin Leisinger }} {{Inprocee…“) |
He9318 (Diskussion | Beiträge) |
||
Zeile 12: | Zeile 12: | ||
|Year=2021 | |Year=2021 | ||
|Booktitle=Proceedings of the 15th ACM Recommender Systems Conference (RecSys'21) | |Booktitle=Proceedings of the 15th ACM Recommender Systems Conference (RecSys'21) | ||
− | |Pages= | + | |Pages=749--752 |
|Publisher=ACM | |Publisher=ACM | ||
}} | }} | ||
Zeile 20: | Zeile 20: | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=The number of datasets is steadily rising, making it increasingly difficult for researchers and practitioners in the various scientific disciplines to be aware of all datasets, particularly of the most relevant datasets for a given research problem. To this end, dataset search engines have been proposed. However, they are based on the users' keywords and thus have difficulties in determining precisely fitting datasets for complex research problems. In this paper, we propose the system at http://data-hunter.io that recommends suitable datasets to users based on given research problem descriptions. It is based on fastText for the text representation and text classification, the Data Set Knowledge Graph (DSKG) with metadata about almost 1,700 unique datasets, as well as 88,000 paper abstracts as research problem descriptions for training the model. Overall, our system demonstrates that recommending datasets facilitates data provisioning and reuse according to the FAIR principles and that dataset recommendation is a promising future research direction. | |Abstract=The number of datasets is steadily rising, making it increasingly difficult for researchers and practitioners in the various scientific disciplines to be aware of all datasets, particularly of the most relevant datasets for a given research problem. To this end, dataset search engines have been proposed. However, they are based on the users' keywords and thus have difficulties in determining precisely fitting datasets for complex research problems. In this paper, we propose the system at http://data-hunter.io that recommends suitable datasets to users based on given research problem descriptions. It is based on fastText for the text representation and text classification, the Data Set Knowledge Graph (DSKG) with metadata about almost 1,700 unique datasets, as well as 88,000 paper abstracts as research problem descriptions for training the model. Overall, our system demonstrates that recommending datasets facilitates data provisioning and reuse according to the FAIR principles and that dataset recommendation is a promising future research direction. | ||
− | |Download= | + | |Download=DataHunter_RecSys2021_v3.pdf |
+ | |Link=https://doi.org/10.1145/3460231.3478882 | ||
|DOI Name=10.1145/3460231.3478882 | |DOI Name=10.1145/3460231.3478882 | ||
|Forschungsgruppe=Web Science | |Forschungsgruppe=Web Science |
Aktuelle Version vom 27. September 2021, 09:36 Uhr
DataHunter: A System for Finding Datasets Based on Scientific Problem Descriptions
DataHunter: A System for Finding Datasets Based on Scientific Problem Descriptions
Published: 2021
Buchtitel: Proceedings of the 15th ACM Recommender Systems Conference (RecSys'21)
Seiten: 749--752
Verlag: ACM
Referierte Veröffentlichung
Kurzfassung
The number of datasets is steadily rising, making it increasingly difficult for researchers and practitioners in the various scientific disciplines to be aware of all datasets, particularly of the most relevant datasets for a given research problem. To this end, dataset search engines have been proposed. However, they are based on the users' keywords and thus have difficulties in determining precisely fitting datasets for complex research problems. In this paper, we propose the system at http://data-hunter.io that recommends suitable datasets to users based on given research problem descriptions. It is based on fastText for the text representation and text classification, the Data Set Knowledge Graph (DSKG) with metadata about almost 1,700 unique datasets, as well as 88,000 paper abstracts as research problem descriptions for training the model. Overall, our system demonstrates that recommending datasets facilitates data provisioning and reuse according to the FAIR principles and that dataset recommendation is a promising future research direction.
Download: Media:DataHunter_RecSys2021_v3.pdf
Weitere Informationen unter: Link
DOI Link: 10.1145/3460231.3478882
Information Retrieval, Natürliche Sprachverarbeitung, Digitale Bibliotheken, Knowledge Discovery, Künstliche Intelligenz