Sentiment analysis,commonly called opinion mining or emotion artificial intelligence(AI),employs biometrics,computational linguistics,nat-ural language processing,and text analysis to systematically identify,extract,m...Sentiment analysis,commonly called opinion mining or emotion artificial intelligence(AI),employs biometrics,computational linguistics,nat-ural language processing,and text analysis to systematically identify,extract,measure,and investigate affective states and subjective data.Sentiment analy-sis algorithms include emotion lexicon,traditional machine learning,and deep learning.In the text sentiment analysis algorithm based on a neural network,multi-layer Bi-directional long short-term memory(LSTM)is widely used,but the parameter amount of this model is too huge.Hence,this paper proposes a Bi-directional LSTM with a trapezoidal structure model.The design of the trapezoidal structure is derived from classic neural networks,such as LeNet-5 and AlexNet.These classic models have trapezoidal-like structures,and these structures have achieved success in the field of deep learning.There are two benefits to using the Bi-directional LSTM with a trapezoidal structure.One is that compared with the single-layer configuration,using the of the multi-layer structure can better extract the high-dimensional features of the text.Another is that using the trapezoidal structure can reduce the model’s parameters.This paper introduces the Bi-directional LSTM with a trapezoidal structure model in detail and uses Stanford sentiment treebank 2(STS-2)for experiments.It can be seen from the experimental results that the trapezoidal structure model and the normal structure model have similar performances.However,the trapezoidal structure model parameters are 35.75%less than the normal structure model.展开更多
Sentiment Analysis, an un-abating research area in text mining, requires a computational method for extracting useful information from text. In recent days, social media has become a really rich source to get informat...Sentiment Analysis, an un-abating research area in text mining, requires a computational method for extracting useful information from text. In recent days, social media has become a really rich source to get information about the behavioral state of people(opinion) through reviews and comments. Numerous techniques have been aimed to analyze the sentiment of the text, however, they were unable to come up to the complexity of the sentiments. The complexity requires novel approach for deep analysis of sentiments for more accurate prediction. This research presents a three-step Sentiment Analysis and Prediction(SAP) solution of Text Trend through K-Nearest Neighbor(KNN). At first, sentences are transformed into tokens and stop words are removed. Secondly, polarity of the sentence, paragraph and text is calculated through contributing weighted words, intensity clauses and sentiment shifters. The resulting features extracted in this step played significant role to improve the results. Finally, the trend of the input text has been predicted using KNN classifier based on extracted features. The training and testing of the model has been performed on publically available datasets of twitter and movie reviews. Experiments results illustrated the satisfactory improvement as compared to existing solutions. In addition, GUI(Hello World) based text analysis framework has been designed to perform the text analytics.展开更多
English text sentiment orientation analysis is a fundamental problem in the field of natural language processing.The traditional word segmentation method can produce ambiguity when dealing with English text.Therefore,...English text sentiment orientation analysis is a fundamental problem in the field of natural language processing.The traditional word segmentation method can produce ambiguity when dealing with English text.Therefore,this paper proposes a novel English text sentiment analysis based on convolutional neural network and U-network.The proposed method uses a parallel convolution layer to learn the associations and combinations between word vectors.The results are then input into the hierarchical attention network whose basic unit is U-network to determine the affective tendency.The experimental results show that the accuracy of bias classification on the English review dataset reaches 93.45%.Compared with many existing sentiment analysis models,it has more accuracy.展开更多
近年来,情感分析是近年来自然语言处理领域备受学者关注的核心研究方向,传统文本情感分析模型只能捕捉文本的表面特征,在不同领域或语境下缺乏泛化能力,难以处理长文本以及语义歧义等问题.针对上述问题,本文设计了基于图神经网络与表示...近年来,情感分析是近年来自然语言处理领域备受学者关注的核心研究方向,传统文本情感分析模型只能捕捉文本的表面特征,在不同领域或语境下缺乏泛化能力,难以处理长文本以及语义歧义等问题.针对上述问题,本文设计了基于图神经网络与表示学习的文本情感分析模型(a text sentiment analysis model based on graph neural networks and representation learning,GNNRL).利用Spacy生成句子的语法依赖树,利用图卷积神经网络进行编码,以捕捉句子中词语之间更复杂的关系;采用动态k-max池化进一步筛选特征,保留文本相对位置的序列特征,避免部分特征损失的问题,从而提高模型的特征提取能力.最后将情感特征向量输送到分类器SoftMax中,根据归一化后的值来判断情感分类.为验证本文所提GNNRL模型的有效性,采用OS10和SMP2020两个文本情感分析数据集进行测试,与HyperGAT、IBHC、BERT_CNN、BERT_GCN、TextGCN模型比较,结果表明,综合accuracy、precision、recall、f14个指标,本文改进的AM_DNN模型均优于其他模型,在文本情感中具有较好的分类性能,并探究了不同优化器的选择对本模型的影响.展开更多
目前情感分析任务经常只聚焦于评论文本本身,忽略了评论者与被评论者的个体偏差特征,会显著影响对文本的整体情感判断。针对上述问题,提出一种融合评论双边个体偏差信息的文本情感分析模型UP-ATL(User and Product-Attention TranLSTM)...目前情感分析任务经常只聚焦于评论文本本身,忽略了评论者与被评论者的个体偏差特征,会显著影响对文本的整体情感判断。针对上述问题,提出一种融合评论双边个体偏差信息的文本情感分析模型UP-ATL(User and Product-Attention TranLSTM)。该模型使用自注意力机制、交叉注意力机制对评论文本与个体偏差信息分别进行双向融合,在融合过程中采用定制化权重的计算方式,以缓解实际应用场景中冷启动带来的数据稀疏问题,最终得到特征充分融合的评论文本和评论双边的表示信息。选取餐饮领域、电影领域的三个真实公开数据集Yelp2013、Yelp2014、IMDB进行效果验证,与UPNN(User Product Neural Network)、NSC(Neural Sentiment Classification)、CMA(Cascading Multiway Attention)、HUAPA(Hierarchical User And Product multi-head Attention)等基准模型进行比较。实验结果表明,相较于比较模型中最好的HUAPA模型,UP-ATL的准确度在三个数据集上依次分别提高了6.9、5.9和1.6个百分点。展开更多
基金supported by Yunnan Provincial Education Department Science Foundation of China under Grant construction of the seventh batch of key engineering research centers in colleges and universities(Grant Project:Yunnan College and University Edge Computing Network Engineering Research Center).
文摘Sentiment analysis,commonly called opinion mining or emotion artificial intelligence(AI),employs biometrics,computational linguistics,nat-ural language processing,and text analysis to systematically identify,extract,measure,and investigate affective states and subjective data.Sentiment analy-sis algorithms include emotion lexicon,traditional machine learning,and deep learning.In the text sentiment analysis algorithm based on a neural network,multi-layer Bi-directional long short-term memory(LSTM)is widely used,but the parameter amount of this model is too huge.Hence,this paper proposes a Bi-directional LSTM with a trapezoidal structure model.The design of the trapezoidal structure is derived from classic neural networks,such as LeNet-5 and AlexNet.These classic models have trapezoidal-like structures,and these structures have achieved success in the field of deep learning.There are two benefits to using the Bi-directional LSTM with a trapezoidal structure.One is that compared with the single-layer configuration,using the of the multi-layer structure can better extract the high-dimensional features of the text.Another is that using the trapezoidal structure can reduce the model’s parameters.This paper introduces the Bi-directional LSTM with a trapezoidal structure model in detail and uses Stanford sentiment treebank 2(STS-2)for experiments.It can be seen from the experimental results that the trapezoidal structure model and the normal structure model have similar performances.However,the trapezoidal structure model parameters are 35.75%less than the normal structure model.
文摘Sentiment Analysis, an un-abating research area in text mining, requires a computational method for extracting useful information from text. In recent days, social media has become a really rich source to get information about the behavioral state of people(opinion) through reviews and comments. Numerous techniques have been aimed to analyze the sentiment of the text, however, they were unable to come up to the complexity of the sentiments. The complexity requires novel approach for deep analysis of sentiments for more accurate prediction. This research presents a three-step Sentiment Analysis and Prediction(SAP) solution of Text Trend through K-Nearest Neighbor(KNN). At first, sentences are transformed into tokens and stop words are removed. Secondly, polarity of the sentence, paragraph and text is calculated through contributing weighted words, intensity clauses and sentiment shifters. The resulting features extracted in this step played significant role to improve the results. Finally, the trend of the input text has been predicted using KNN classifier based on extracted features. The training and testing of the model has been performed on publically available datasets of twitter and movie reviews. Experiments results illustrated the satisfactory improvement as compared to existing solutions. In addition, GUI(Hello World) based text analysis framework has been designed to perform the text analytics.
文摘English text sentiment orientation analysis is a fundamental problem in the field of natural language processing.The traditional word segmentation method can produce ambiguity when dealing with English text.Therefore,this paper proposes a novel English text sentiment analysis based on convolutional neural network and U-network.The proposed method uses a parallel convolution layer to learn the associations and combinations between word vectors.The results are then input into the hierarchical attention network whose basic unit is U-network to determine the affective tendency.The experimental results show that the accuracy of bias classification on the English review dataset reaches 93.45%.Compared with many existing sentiment analysis models,it has more accuracy.
文摘近年来,情感分析是近年来自然语言处理领域备受学者关注的核心研究方向,传统文本情感分析模型只能捕捉文本的表面特征,在不同领域或语境下缺乏泛化能力,难以处理长文本以及语义歧义等问题.针对上述问题,本文设计了基于图神经网络与表示学习的文本情感分析模型(a text sentiment analysis model based on graph neural networks and representation learning,GNNRL).利用Spacy生成句子的语法依赖树,利用图卷积神经网络进行编码,以捕捉句子中词语之间更复杂的关系;采用动态k-max池化进一步筛选特征,保留文本相对位置的序列特征,避免部分特征损失的问题,从而提高模型的特征提取能力.最后将情感特征向量输送到分类器SoftMax中,根据归一化后的值来判断情感分类.为验证本文所提GNNRL模型的有效性,采用OS10和SMP2020两个文本情感分析数据集进行测试,与HyperGAT、IBHC、BERT_CNN、BERT_GCN、TextGCN模型比较,结果表明,综合accuracy、precision、recall、f14个指标,本文改进的AM_DNN模型均优于其他模型,在文本情感中具有较好的分类性能,并探究了不同优化器的选择对本模型的影响.
