Emotion Analysis Of Micro Blog Comment Based On Ensemble Learning

Weibo has the characteristics of fast user release of information and fast transmission of information,and has become the main social media for people.Netizens will express their emotional views on different events by posting microblogs and comments.Sentiment analysis of Weibo comments plays a major role in network monitoring,public sentiment guidance,and public opinion monitoring.Manually mining and analyzing the emotions contained in comments consumes a lot of manpower,and the efficiency of excavate emotions is very poorly,So more people are starting to do emotional analysis studies.This article uses different methods to analyze the sentiment of Weibo text,and the main work is as follows:When conducting sentiment analysis experiments,because of the desire to improve the results of classification,this paper established a basic sentiment dictionary,and then expanded the modifier dictionary and the negative word dictionary,and finally through the analysis of the characteristics of Weibo text and the SO-PMI algorithm,an emoji dictionary and a network popular word dictionary are established,thus forming a Weibo emotion dictionary.Through comparative experiments,the effectiveness of the Weibo emotion dictionary for sentiment analysis was verified.In experiments conducted through machine learning,the TF-IDF model is improved by analyzing the characteristics of existing word vector models,and the multiplication of the weight of degree adverbs and their corresponding modifiers is added into the calculation of the weight of TF-IDF,get the TF-IDF-E algorithm.Then combined with the word vector model of Word2 Vec,the improved weighted word vector model is obtained.The weighted emotion word vector contains information about the original meaning of the word,and adds information about whether the emotion is strong or not.When choosing a classification method for machine learning,three classification algorithms are selected in this paper,on the basis of which,the experiments of integrated classifiers are carried out.From the results of the experiment,we can know that the model proposed in this paper can significantly improve the accuracy of sentiment analysis..When choosing different classification algorithms for experiments,combining the weighted word vector model,the highest accuracy of single classifier is 84.29%,and the highest accuracy of integrated classifier is 86.73%.Therefore,the integration model used in this paper has better classification effect.