[Retracted] Parameter Optimization of Educational Network Ecosystem Based on BERT Deep Learning Model

Table 3

Comparison of experimental results combined with a dynamic word vector (unit: %).

Model	Accuracy
BERT	90.14
ULMFIT	91.21
SentiBERT	90.94
BERT + MC-BiGRU-capsule	91.89
MC-BiGRU-capsule	91.55