Fake online review recognition algorithm and optimisation research based on deep learning

Convolutional neural network is a deep multi-layer neural network model composed of regular connections of multi-layer neurons [14], specifically including input layer, hidden layer (convolution layer, pooling layer) and output layer. Since the convolutional neural network has the feature of sparse connection, that is, local connection, each node of the convolutional layer in the model can only be connected to the local region of the upper layer. Therefore, the convolutional neural network can be applied to the recognition model of false comments. Through the design of the convolutional kernel, the information of the text can be extracted, and the semantics of adjacent words of the text can be recognised due to the characteristics of local connection, which is suitable for the application in short text classification and recognition algorithm.

Recurrent neural network is also a deep neural network model, but different from the convolutional neural network; it has the function of self-connection between each hidden layer, which enables the information of elements to be transmitted layer by layer, that is, the recurrent neural network has the function of ‘memory’ [14]. Due to the characteristics of its own structure, it makes the processing of sequence information more accurate, so it is also commonly used to process text and sound data.

In the process of text processing, the recurrent neural network not only processes the current word, but also transmits the information of the word to the next word to be processed by weight. Therefore, through a series of weight multiplication, the gradient explosion will occur when |W| > 1, and the gradient will disappear when |W| < 1. To solve these problems, scholars proposed the LSTM and gated recurrent unit (GRU) [16].

The short text of an online review is made up of sentences, and each sentence is made up of a number of words, that is, X = [x₁,...,x_n]. The word vector in the model needs to be initialised, and the normal random distribution sampling is selected to obtain the initial value.

The generation of fake reviews not only includes the comments generated by the fake shopping behaviour, but also includes the fake comments generated by the normal shopping behaviour in the evaluation link. Therefore, in addition to using the hybrid neural network model to extract the global and local features of the text, we should first eliminate the comments generated by the fake reviewers through the fake shopping behaviour. Therefore, the following indicators are used to quantify the shopping behaviour of reviewers, and then the false reviewers are identified, so as to improve the overall recognition effect of the model.

The mixed neural network model uses the convolutional network model to represent the local features of text, which is realised through a convolutional kernel Y ∈ R^t∗d whose width and dimension of word vector are d, and step size is t. Specifically, local features are extracted by the following formula: (1) Nij=f(Y⊙Xj:j+t−1+b) {N_{ij}} = f\left( {Y \odot {X_{j:j + t - 1}} + b} \right) where f is the nonlinear activation function and b is the offset value. In this paper, the Relu function with high universality is selected as the activation function. Each convolution feature is connected by the following formula: (2) Ni=[Ni1,Ni2,…,Ni(n−t+1)] {N_i} = \left[ {{N_{i1}},{N_{i2}}, \ldots ,{N_{i\left( {n - t + 1} \right)}}} \right]

As shown in the above formula, each convolution kernel will extract n − t + 1 local features. In this paper, k convolution kernels are adopted to reduce the feature dimension through the maximum pooling method, extract the optimal feature N_imax of each local feature and connect the optimal features. The specific methods are as follows: (3) Xlocal=[N1max,N2max…,Nkmax] {X_{local}} = \left[ {{N_{1\max }},{N_{2\max }} \ldots ,{N_{k\max }}} \right]

The global features of the model are extracted by the recurrent neural network. Due to the potential problems of gradient explosion or gradient disappearance caused by the short-term memory function of the recurrent neural network mentioned above, LSTM was adopted in this paper to optimise the model and to avoid the above problems by adding a hidden layer and a gated unit. Bidirectional LSTM, namely BI-LSTM, is to learn the text from the front and back directions, so that the model has a better effect. Specific output status is as follows: (4) hi=F(xi,hi−1) {h_i} = F\left( {{x_i},{h_{i - 1}}} \right) where h_i is the output state, h_i−1 is the output of the previous neuron and x_i is the current word vector. F function is the operation on LSTM mentioned in the work of Chung et al. [14], which will not be repeated here. And BI-LSTM is a vector that carries out a bidirectional combination sequence of the above outputs. The specific formula is as follows: (5) Xhidden=[hl1:n,hr1:n] {X_{hidden}} = \left[ {h{l_{1:n}},h{r_{1:n}}} \right]

The next step is to extract the global features of the statement from the hidden layer. Since the forward and reverse output sequences obtained in the previous step only contain the global features, different methods can be selected in the extraction process. In the following paper, the advantages and disadvantages of the extraction method can be judged by comparing the recognition accuracy. Specifically, the global features of the hidden layer are extracted by the following three methods: (6) Xglobal−1=[hlend,hrend] {X_{global - 1}} = \left[ {h{l_{end}},h{r_{end}}} \right] (7) Xglobal−2=[hlaverage,hraverage] {X_{global - 2}} = \left[ {h{l_{average}},h{r_{average}}} \right] (8) Xglobal−3=[hlattention,hraverage] {X_{global - 3}} = \left[ {h{l_{attention}},h{r_{average}}} \right]

The first approach is to take the final state of hl and hr as the global feature, which is later referred to as hybird-e. The second method is to take the average state of hl and hr as the global feature, which is later denoted as hybird-av. The third method uses the algorithm in the attention mechanism model to take the weight of each useful state as the final recognised global feature, which is later referred to as hybird-at [17].

Connect the global variable obtained in the previous step to the local variable, and the specific formula is as follows: (9) X=[Xlocal,Xglobal] X = \left[ {{X_{local}},{X_{global}}} \right]

Next, the full connection layer fusion is implemented, and its output is a vector representation containing global and local features. The specific formula is as follows: (10) y=Wn×(X⊙Wq)+bn y = {W_n} \times \left( {X \odot {W_q}} \right) + {b_n}

Finally, the Softmax classifier is used to classify the above vectors to achieve the ultimate goal of text recognition. The specific operation is as follows: (11) Pn=exp(yn)Σn′∈Nexp(yn′) {P_n} = {{\exp \left( {{y_n}} \right)} \over {{\Sigma _{n^\prime \in N}}\exp \left( {y_{n^\prime}} \right)}}

Activation functions are introduced to add a non-linear element to a model that is linear at every level. Since neurons can only be activated when a certain threshold is reached, the selection of Relu function is more consistent with the characteristics of biological neurons [16], and its specific expression formula (12) and function image (Figure 3) are as follows: (12) Relu(x)=max(0,x) {\mathop{\rm Re}\nolimits} lu\left( x \right) = \max \left( {0,x} \right)

Fig. 3

The Dropout layer is set between the full connection layer and the Softmax layer to avoid over-fitting of the model. The specific operation is to discard the neurons probabilistically during the operation of the model, so as to reduce the training parameters and avoid the occurrence of overfitting of the model. The propagation formula of neurons is as follows: (13) riu∼Bernoulli(p) r_i^u \sim Bernoulli\left( p \right) (14) yv=ru*yu {y^v} = {r^u}*{y^u} (15) Ziu+1=Wiu+1yv+biu+1 Z_i^{u + 1} = W_i^{u + 1}{y^v} + b_i^{u + 1} (16) yiu+1=f(Ziu+1) y_i^{u + 1} = f\left( {Z_i^{u + 1}} \right)

The model descent method aims to improve the training time of the model and enhance the robustness of the model by selecting a small amount of data several times in the process of training the model. The specific formula is as follows: (17) θi'=θi−α∑k=1n(hθ(xk)−yk)xik \theta _i^\prime = {\theta _i} - \alpha \sum\nolimits_{k = 1}^n {\left( {{h_\theta }\left( {{x^k}} \right) - {y^k}} \right)x_i^k}