FEBDNN: fusion embedding-based deep neural network for user retweeting behavior prediction on social networks

Abstract

Due to the fast growing amount of user generated content (UGC) on social networks, the prediction of retweeting behavior is attracting significant attention in recent years. However, the existing studies tend to ignore the influence of implicit social influence and group retweeting factor factors. Also, it is still challenging to consider all related factors into a unified framework. To solve the above disadvantages, we propose a novel deep neural network fusion embedding-based deep neural network (FEBDNN) through the perspective of user embedding and tweets embedding for the author and the user’s historical tweets. Firstly, we propose dual auto-encoder (DAE) network for user embedding by integrating user’s basic features, explicit and implicit social influence and group retweeting factor. Then, we utilize the attention-based F_BLSTM_CNN(A_F_BLSTM_CNN) model for historical tweets’ representative embedding based on the combination of convolutional neural network (CNN) and bidirectional long short-term memory (BLSTM). Finally, we concatenate these embedding features into a vector and design a hidden layer and a fully connected softmax layer to predict the retweeting label. The experimental results demonstrate that the FEBDNN model compares favorably performance against the state-of-the-art methods.

Image recognition of traditional Chinese medicine based on deep learning

“…Deep learning technology has been gradually applied to Natural language processing, voice, image and other aspects , and has made breakthrough progress in the application field of artificial intelligence, as well as excellent achievements in many fields (Wang et al, 2022). In order to solve the image recognition of traditional Chinese medicine, deep learning technology is used to complete the recognition of traditional Chinese medicine, which not only effectively solves the problems of misjudgment and low efficiency caused by human factors, but also has high detection and recognition rate, convenient operation, and greatly saves time and labor costs.…”

Retweet Prediction Using Multi-Layer Perceptron Optimized by The Swarm Intelligence Algorithm

“…where 𝑤 𝑖𝑗 1 is the weight between the first hidden layer neurons and the second hidden layer neurons. Next, the output from the neurons in the second hidden layer will become input for the output neurons, so that we get…”

“…The tweet uploader is the main actor in the dissemination of information on Twitter, therefore it is important to understand the influence of users on retweet predictions. The number of followers and followees is one of the factors that influence whether a tweet gets retweets or not [1][2][3] [4]. Strong interaction between the uploader and his followers will influence his tweets to be retweeted by his followers [5] [6].…”

“…The classification method used to predict whether a tweet will get a retweet or not, among other things, Bayesian Poisson Factorization (BPF) Model [9], Log-Linear Regression [10], Artificial Neural Network [14] [11] , Deep Neural Network [1] [3], Support Vector Machine(SVM) optimized by Cuckoo Search algorithm [5], XGBoost [2][13], Logistic Regression [8][11] [7], MAKER-RIMER Prediction Model [12], SVM [11][7][4], Random Forest [11] [13] [7] [4], Naive Bayes [11] [4], Probabilistic Matrix Factorization Method [6], Decision Tree [7], K-Nearest Neighbors (KNN) [7] .…”

Special issue on deep learning for time series data

“…In order to improve temporal data processing in time series classification, Modiri et al [4] introduce a novel algorithm obtained via the fusion of nonlinear optimal control theory and reservoir computing. Wang et al [5] propose a novel unified deep neural network: fusion embedding-based deep neural network (FEBDNN) from the perspective of embedding learning that jointly combines the user embedding features and the tweets embedding features to improve the performance of retweeting prediction task. Streaming time series classification is an essential topic for many real-world applications.…”