Common Laws Driving the Success in Show Business

Table 4

Performance comparison of our methods and a recent study NatComm19 [1] in the prediction of the AM on the subset (AM ≥ 10) of the test data.

	Actor	Actress	Actor	Actress
	L ≥ 20, AM ≥ 10	L ≥ 20, AM ≥ 10	5 = < L < 20, AM ≥ 10	5 = < L < 20, AM ≥ 10
C1 : C2	0.6481	0.4169	0.6053	0.3348
Baseline accuracy	0.7275	0.7968	0.7668	0.8173
MM_ours
F1 score	0.9409	0.9591	0.9202	0.9530
Precision	0.9355	0.9612	0.9418	0.9780
Recall	0.9463	0.9571	0.8995	0.9293
Accuracy	0.9279	0.9422	0.9024	0.9313
MAO_ours
F1 score	0.9389	0.9557	0.9276	0.9563
Precision	0.9551	0.9729	0.9538	0.9836
Recall	0.9232	0.9391	0.9029	0.9306
Accuracy	0.9270	0.9387	0.9118	0.9359
MAE_ours
F1 score	0.9396	0.9559	0.9377	0.9643
Precision	0.9414	0.9664	0.9338	0.9761
Recall	0.9378	0.9457	0.9415	0.9528
Accuracy	0.9264	0.9386	0.9217	0.9467
NatComm19MM
F1 score	0.7688	0.8008	0.8114	0.7607
Precision	0.9299	0.8879	0.7321	0.6371
Recall	0.6552	0.7292	0.9101	0.9439
Accuracy	0.8460	0.8916	0.8367	0.8478
NatComm19MAO
F1 score	0.7681	0.7989	0.8085	0.7559
Precision	0.9280	0.8841	0.7250	0.6297
Recall	0.6552	0.7287	0.9137	0.9453
Accuracy	0.8453	0.8909	0.8371	0.8449
NatComm19MAE
F1 score	0.7377	0.7790	0.8127	0.7616
Precision	0.9373	0.8956	0.7518	0.6431
Recall	0.6082	0.6892	0.8843	0.9337
Accuracy	0.8330	0.8823	0.8429	0.8502

MM_ours denotes the prediction model trained by the mixed data of an actor and actress; MAO_ours denotes the prediction model trained by the data of an actor only; MAE_ours denotes the prediction model trained by the data of an actress only; MM_NatComm19 denotes the model of NatComm19 [1] trained by the mixed data of an actor and actress, and the learned threshold d = 6.1523; MAO_NatComm19 denotes the model of NatComm19 [1] trained by the data of an actor, and the learned threshold d = 6.9580; MAE_NatComm19 denotes the model of NatComm19 [1] trained by the data of an actress, and the learned threshold d = 5.6640.