Common Laws Driving the Success in Show Business

Table 5

Performance comparison of our methods and a recent study NatComm19 [1] in the prediction of the AM on the subset (AM ≥ 15) of the test data.

	Actor	Actress	Actor	Actress
	L ≥ 20, AM ≥ 15	L ≥ 20, AM ≥ 15	5 = < L < 20, AM ≥ 15	5 = < L < 20, AM ≥ 15
C1 : C2	0.5271	0.3253	0.6292	0.3429
Baseline accuracy	0.7683	0.8439	0.7940	0.8467
MM_ours
F1 score	0.9563	0.9725	0.9236	0.9583
Precision	0.9600	0.9756	0.9548	0.9883
Recall	0.9527	0.9694	0.8945	0.9301
Accuracy	0.9434	0.9584	0.9021	0.9358
MAO_ours
F1 score	0.9533	0.9697	0.9336	0.9618
Precision	0.9750	0.9832	0.9692	0.9934
Recall	0.9326	0.9566	0.9005	0.9322
Accuracy	0.9401	0.9548	0.9159	0.9414
MAE_ours
F1 score	0.9560	0.9710	0.9340	0.9638
Precision	0.9632	0.9794	0.9306	0.9758
Recall	0.9489	0.9627	0.9375	0.9520
Accuracy	0.9425	0.9562	0.9179	0.9458
NatComm19MM
F1 score	0.7647	0.7990	0.8161	0.7425
Precision	0.9303	0.8555	0.7581	0.6161
Recall	0.6492	0.7495	0.8837	0.9340
Accuracy	0.8600	0.9099	0.8593	0.8614
NatComm19MAO
F1 score	0.7608	0.8043	0.7978	0.7588
Precision	0.9230	0.8660	0.7282	0.6345
Recall	0.6470	0.7508	0.8822	0.9437
Accuracy	0.8610	0.9096	0.8491	0.8639
NatComm19MAE
F1 score	0.7361	0.7883	0.7954	0.7552
Precision	0.9268	0.8586	0.7455	0.6391
Recall	0.6105	0.7286	0.8525	0.9230
Accuracy	0.8530	0.9059	0.8489	0.8671

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.