. 2019 Feb 20;21(2):e12783. doi: 10.2196/12783

Table 8.

Performance in the Chinese subtask (6 participating systems and 2 baseline systems).

System ID^a	Exact match^b	F1		Precision		Recall		Hamming loss
System ID^a	Exact match^b	Micro	Macro	Micro	Macro	Micro	Macro	Hamming loss
NAIST-zh-2	0.880	0.920	0.906	0.899	0.887	0.941	0.925	0.019
NAIST-zh-3	0.878	0.919	0.904	0.899	0.885	0.940	0.924	0.019
NAIST-zh-1	0.877	0.918	0.904	0.899	0.887	0.938	0.921	0.020
TUA1-zh-3	0.786	0.860	0.844	0.772	0.760	0.970	0.971	0.037
SVM-unigram	0.780	0.858	0.843	0.831	0.815	0.888	0.883	0.034
TUA1-zh-1	0.773	0.853	0.838	0.766	0.753	0.963	0.965	0.039
SVM-bigram	0.767	0.850	0.835	0.824	0.806	0.878	0.876	0.036
TUA1-zh-2	0.719	0.824	0.809	0.712	0.710	0.978	0.982	0.049

^aThe system ID comprises the group ID (see Multimedia Appendix 1), the abbreviation of subtask (zh indicates Chinese subtask), and the system number from 1 to 3 since each group can submit 3 systems per subtask.

^b The results are ordered by exact match accuracy.