A Neural Network-Inspired Approach for Improved and True Movie Recommendations

Table 1

Nomenclatures and description.

Nomenclature	Description
	Document/review
	Sentence
	Word
	Review corpus
	Movie
	Length of a sentence
	Hidden state
	Total movie sites
	Biases
	Twitter likes
	Timestep
	j-th movie sentiment at site
	j-th movie sentiment at site
	j-th movie sentiment at site
	j-th movie rating at site
	j-th movie rating at site
	j-th movie rating at site
	j-th movie total quantitative score
	Final recommendation score
AWAS	Aggregated weighted average sentiment
Multivariate	Multivariate final score
	Input gate
	Output gate
	Forget gate
	Activation function
	Biases
	Weight vector
	Vector transpose
	Timestep
	Multiplication
ht	Hidden state at t timestep
ht−1	Hidden state at t−1 (previous) timestep
W	Weight matrix for input to hidden layers at t timestep
∅	tanh is an activation function
	Input at timestep (t)
	j-th movie votes at site
	j-th movie votes at site
	j-th movie votes at site
	Loss
AS	Aggregated sentiment
WAS	Weighted average sentiment