Résumé
The current society faces the exponential challenges of collecting and valuing data. No matter the field, data has become the main point of interest to explore our past, to understand our present, and to enhance our future. This is also the case for the so-called Scholarly Data field which refers to every kind of data that is linked to any form of scientific production.While this type of data has already been subject to studies, in the current work we focus on investigating what are the key drivers that play a significant role in the impact of the scholar. In other words, we try to understand which features influence the « success » of a scientific production and how.
We first review the theoretical background regarding the Scholarly world and the Machine Learning tools. We then present the methodology we applied; the data we collected, and how we used it. We conclude with the results and the discussion parts that aim to provide users with recommendations based on what we found with the Machine Learning models.
| la date de réponse | 2021 |
|---|---|
| langue originale | Anglais |
| L'institution diplômante |
|
| Superviseur | Sarah Bouraga (Promoteur) |