Research Article

An Assistant Teaching System of English Creative Writing Based on Semantic Mining

Table 2

The comparison algorithms.

NumberAlgorithmTheoryOperation principle

1Literature [24]Matrix decompositionThe rating matrix is used as input, the inner product of the low-rank matrix of users and items is used to represent the rating, and the objective function is minimized by the alternate least squares (ALS) technique

2Literature [25]Probability matrix decompositionOnly score data is used for collaborative filtering, and Gaussian distribution is introduced to model the underlying factors of users and items

3Literature [26]Parallel neural networkAn additional sharing layer on top of the two neural networks connects the two parallel networks so that the learned user and project potential factors can interactively predict ratings. This model proves that the sparsity problem can be effectively alleviated by using comment text