Hashtag Recommendation Using LSTM Networks with Self-Attention

Abstract

On Twitter, people often use hashtags to mark the subject of a tweet. Tweets have specific themes or content that are easy for people to manage. With the increase in the number of tweets, how to automatically recommend hashtags for tweets has received wide attention. The previous hashtag recommendation methods were to convert the task into a multi-class classification problem. However, these methods can only recommend hashtags that appeared in historical information, and cannot recommend the new ones. In this work, we extend the self-attention mechanism to turn the hashtag recommendation task into a sequence labeling task. To train and evaluate the proposed method, we used the real tweet data which is collected from Twitter. Experimental results show that the proposed method can be significantly better than the most advanced method. Compared with the state-of-the-art methods, the accuracy of our method has been increased 4%.

Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms

“…GA-ConvGRU consists of two opposite learning systems, namely a generator and a discriminator. Lin uses the ConvGRU model as a generator and attaches a five-layer convolutional neural network as a discriminator [21]. These two systems learn by playing the minimax game.…”

A Method of Optimizing Network Topology Structure Combining Viterbi Algorithm and Bayesian Algorithm

“…The result obtained by using the regression model and the prediction method is very small, and there is a decline in some indicators. After studying the literature related to this article, add relevant theoretical and experimental analysis [20][21][22][23][24] .Comprehensive consideration, the use of MBPR performs better.…”

Traffic prediction using MSSBiLS with self‐attention model

“…Moreover taking into account the demesne facts, deep learning models learn highlights and evolution straightforwardly from the data 15–17 . They accelerate the mode of data preparation and can study more intricate data patterns in a replete manner 18 . These methods have been appeared to deliver more exact outcomes than conventional regression‐based modeling.…”

“…[15][16][17] They accelerate the mode of data preparation and can study more intricate data patterns in a replete manner. 18 These methods have been appeared to deliver more exact outcomes than conventional regression-based modeling. It is accounted for that counterfeit recurrent neural networks (RNNs) with memory, for example, long short-term memory (LSTM) and gated recurrent unit (GRU), are better analyzed than autoregressive integrated moving average (ARIMA) with a huge edge.…”