Semantic sentiment analysis method fusing in-depth features and time sequence models

1. A semantic sentiment analysis method fusing in-depth features and time sequence models, comprising steps of:

S 1 , preprocessing a text to convert the text into a uniformly formatted matrix of word vectors;

S 2 , extracting local semantic emotional text features and contextual semantic emotional text features by taking the matrix of word vectors as input of each of a convolutional neural network and a bidirectional long short-term memory network, wherein the local semantic emotional text features are extracted by using the convolutional neural network, and the contextual semantic emotional text features are extracted by using the bidirectional long short-term memory network;

S 3 , weighting the local semantic emotional text features and the contextual semantic emotional text features by using an attention mechanism to generate fused semantic emotional text features,

wherein according to settings, outputs of the bidirectional long short-term memory network and the convolutional neural network have a same width with each other, but have different lengths from each other, and wherein according to a scaled dot-product attention mechanism, a corresponding attention weight formula is,

w

s

=

exp

⁡

(

score

⁡

(

h

c

,

h

l

)

)

∑

exp

⁡

(

score

⁡

(

h

c

,

h

l

)

)

where h c and h l are the outputs of the convolutional neural network and the bidirectional long short-term memory network, respectively, and score(h c ,h l ) is an alignment score which measures a similarity between h c and h l , and

where by using the attention weight w s and h l T , fused feature vectors h cl carrying key emotional information are calculated, and a vector of the last dimension of h cl is taken and recorded as h attention to serve as a fused semantic emotional text feature vector to be finally output;

S 4 , connecting the local semantic emotional text features, the contextual semantic emotional text features and the fused semantic emotional text features to generate global semantic emotional text features; and

S 5 , performing final text emotional semantic analysis and recognition by using a softmax classifier and taking the global semantic emotional text features as input.

2. The method according to claim 1 , wherein converting the text into a uniformly formatted matrix of word vectors includes:

S 11 , word cutting, in which the word cutting is applied on a text of Chinese, but no word cutting is applied on a text of English;

S 12 , cleaning, in which the text subjected to the word cutting is cleaned; and

S 13 , word embedding, in which the cleaned text is subjected to word embedding with pre-trained word vectors to obtain the matrix of word vectors.

3. The method according to claim 2 , wherein converting the text into a uniformly formatted matrix of word vectors further includes:

data length processing, in which a length of each data input sequence is set to N, wherein a sentence with a text length less than N is filled up with zero vectors, while a sentence with a text length greater than the length N is cut off, so that the matrix of word vectors of data of each text is of N×d.

4. The method according to claim 2 , wherein converting the text into a uniformly formatted matrix of word vectors further includes:

cross-language word embedding, in which a conversion matrix that serves as a conversion bridge between vocabulary vectors of two different languages is found and used so that word vectors of the two different languages are more approximate to each other.

5. The method according to claim 1 , wherein to generate global semantic emotional text features is to connect the local semantic emotional text features h CNN , the contextual semantic emotional text features h LSTM , and the fused semantic emotional text features h attention into the global semantic emotional text features C=[h CNN ,h LSTM ,h attention ].

6. The method according to claim 1 , wherein the global semantic emotion text features are input to be processed through a fully connected layer and then the softmax classifier for implementation of the final text emotional semantic analysis and recognition.

7. The method according to claim 6 , wherein the text emotional semantic analysis and recognition uses a cross-entropy loss function for model training.