Abstract | ||
---|---|---|
Although existing digital libraries such as Google Scholar and CiteSeerX propose advanced search functionalities, they do not take into consideration whether the user is new or specialized in the research domain of his query. As a result, neophytes can spend a lot of time checking documents that are not adapted to their initial information need. In this paper, we propose NeoTex, a machine learning based approach that combines content-based retrieval and citation graph measures to propose documents adapted to new researchers. The contributions of our work are: designing a model for scientific retrieval suited to neophytes, defining an evaluation protocol with realistic ground truths, and testing the model on a large real collection from a national digital library. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICDAR.2017.60 | 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) |
Keywords | Field | DocType |
Machine Learning,Digital Libraries,Citation Graph | Information needs,Computer science,Supervised learning,Context model,Citation graph,Artificial intelligence,Digital library,Machine learning | Conference |
Volume | ISSN | ISBN |
01 | 1520-5363 | 978-1-5386-3587-2 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bissan Audeh | 1 | 7 | 5.23 |
Michel Beigbeder | 2 | 72 | 23.49 |
Christine Largeron | 3 | 148 | 30.40 |