Table 2.

Specific parameter settings.

Parameters	Value
Optimiser	Adagrad
Learning Rate	0.1
Learning rate update speed	100
Word vector dimension	100
N value in the TOP-N recommendation model	{5, 10, 15, 20}
Number of latent factors in matrix decomposition recommendation model	50
Number of threads in FastText classification model	12
Value of n-gram in FastText classification model	1
Maximum number of iterations of the algorithm	500
Ranking of the ranking function	300
lambda value of the anonymous function	0.1
Matrix parameters of user interest	1
Matrix parameters of user disinterest	0