The openAlex new author data was out on July 25, and was finally announced on Aug 11, 2023. I did some tests after July 25 and also after Aug 11. I noticed that there are some intermedia changes in the Author data.
In general, the new author data is much better in terms of accuracy, compared to the previous version. However, there are still issues for both author and work. I have tested some cases. see https://github.com/yhan818/openalexR-test/issues/7
Hi, All,
The openAlex new author data was out on July 25, and was finally announced on Aug 11, 2023. I did some tests after July 25 and also after Aug 11. I noticed that there are some intermedia changes in the Author data.
It seems to me that it uses cosine_similarity to measure the similarity and XGBoost of matching an author with his/her name. see code https://github.com/ourresearch/openalex-name-disambiguation/tree/main/V3/002_Data_Processing_Modeling_Clustering
In general, the new author data is much better in terms of accuracy, compared to the previous version. However, there are still issues for both author and work. I have tested some cases. see https://github.com/yhan818/openalexR-test/issues/7
So what are your views on the latest updates?