APP-Store Review Sentiment Analysis Based on Deep Learning
LI Xin
LI Xiaoge
Abstract：Online shopping has become a major way of life,using text sentiment analysis to analyze the comment data of the shopping platform has become the direction of development. Sentiment analysis methods commonly used is mainly based on the tradi?tional machine learning methods,and it requires manual marking sentiment dictionary ,but the sentiment dictionary needs to be constructed by person,in order to reduce the dependence on artificial sentiment dictionary,so deep learning analysis method has become a hot spot. This paper uses words embedding and word embedding of different size as input,using a sentiment analysis meth?od based on long short term memory neural network and attention model,text sentiment analysis method proposed in this paper owns higher average accuracy rate of the macro,macro average recall and F1 value than the traditional machine learning method through the experimental results.
Keywords：sentiment analysisword embeddinglong short-term memoryattention model
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 2417-2422,2433 )