The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

Multilingual Wikipedia

In June 2020 the work The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation was on the 37th place in the ranking of the most reliable and popular publications with DOI number in multilingual Wikipedia from readers' point of view (PR-score). If we consider only frequency of appearance of this source in references of Wikipedia articles (F-score), this work was on the 61,891st place in June 2020. From Wikipedians' point of view, "The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation" is the 13,781st most reliable publication with DOI number in different language versions of Wikipedia (AR-score).

PR-score:
37th place
2,219,400
-462,944
AR-score:
13,781st place
8,644
-409
F-score:
61,891st place
11
0

English Wikipedia (en)

PR-score:
15th place
2,217,025
-463,876
AR-score:
7,180th place
8,594
-416
F-score:
21,754th place
10
0

Japanese Wikipedia (ja)

PR-score:
23,203rd place
2,375
+933
AR-score:
35,726th place
50
+8
F-score:
63,082nd place
1
0

Popularity and reliability assessment of sources in references of Wikipedia in different languages. Data extraction based on complex method using Wikimedia dumps in July 2020. To find the most popular and reliable sources we used information about over 200 million references of Wikipedia articles. More details in the research "Modeling Popularity and Reliability of Sources in Multilingual Wikipedia". Values for PR-score and AR-score were additinaly increased 100 times (to distinguish smaller values in the ranking).

Useful links: