Text Sentiment Analysis Based on Multi-Layer Bi-Directional LSTM with a Trapezoidal Structure

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.

Text Sentiment Analysis Using Frequency-Based Vigorous Features

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.

English Text Sentiment Analysis Based on Convolutional Neural Network and U-network

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.

针对文本情感分类任务的textSE-ResNeXt集成模型

针对深度学习方法中文本表示形式单一,难以有效地利用语料之间细化的特征的缺陷,利用中英文语料的不同特性,有区别地对照抽取中英文语料的特征提出了一种新型的textSE-ResNeXt集成模型。通过PDTB语料库对语料的显式关系进行分析,从而截取语料主要情感部分,针对不同中、英文情感词典进行情感程度关系划分以此获得不同情感程度的子数据集。在textSE-ResNeXt神经网络模型中采用了动态卷积核策略,以此对文本数据特征进行更为有效的提取,模型中融合了SEnet和ResNeXt,有效地进行了深层次文本特征的抽取和分类。将不同情感程度的子集上对textSE-ResNeXt模型采用投票集成的方法进一步提高分类效率。分别在中文酒店评论语料和六类常见英文分类数据集上进行实验。实验结果表明了本模型的有效性。

Sentiment classification model for bullet screen based on self-attention mechanism

With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.

基于BERT-TextCNN的中文短文本情感分析

外卖商家和平台留住客户的重点就是要依据客户的需求制定个性化的服务。因此,本文提出一种基于BERT(Bidirectional Encoder Representation from Transformers)网络与文本卷积神经网络(Convolutional Neural Networks,TextCNN)相结合的BERT-TextCNN网络模型。该模型从外卖中文短文本评论中得到更多的情感信息。最后,在外卖中文评论数据集上进行实验,对比BERT、TextCNN、BERT-TextCNN模型的准确性、稳定性和耗时程度。实验结果证明:BERT-TextCNN的准确率有提升,该方法能更准确地进行中文文本情感分析。

基于TextCNN的文本情感分类系统

通过分析用户在线评论的文本信息来预测消费者的网购偏好意愿,进而提高消费者的满意度成为众多企业的需求.但庞大的评论数据量使得人工手动对评论文本进行分类打标签难以实现,结合Word2vec和TextCNN模型实现对在线评论进行文本情感分类.对评论文本进行规格化处理,通过结巴分词库等对已处理数据进行分词,即提取关键字词.使用Word2vec工具对每个分词进行词向量的训练,得到word embedding权重矩阵作CNN模型的嵌入层,采用TextCNN模型训练得到本文的情感分类模型.相比于直接用传统的卷积神经网络CNN默认的词嵌入层,本文训练出来的神经网络模型效果更佳.

A Lightweight Sentiment Analysis Method

The emergence of big data leads to an increasing demand for data processing methods.As the most influential media for Chinese domestic movie ratings,Douban contains a huge amount of data and one can understand users'perspectives towards these movies by analyzing these data.In this article,we study movie's critics from the Douban website,perform sentiment analysis on the data obtained by crawling,and visualize the results with a word cloud.We propose a lightweight sentiment analysis method which is free from heavy training and visualize the results in a more conceivable way.

Chinese micro-blog sentiment classification through a novel hybrid learning model

With the rising and spreading of micro-blog, the sentiment classification of short texts has become a research hotspot. Some methods have been developed in the past decade. However, since the Chinese and English are different in language syntax, semantics and pragmatics, sentiment classification methods that are effective for English twitter may fail on Chinese micro-blog. In addition, the colloquialism and conciseness of short Chinese texts introduces additional challenges to sentiment classification. In this work, a novel hybrid learning model was proposed for sentiment classification of Chinese micro-blogs, which included two stages. In the first stage, emotional scores were calculated over the whole dataset by utilizing an improved Chinese-oriented sentiment dictionary classification method. Data with extremely high or low scores were directly labeled. In the second stage, the remaining data were labeled by using an integrated classification method based on sentiment dictionary, support vector machine(SVM) and k-nearest neighbor(KNN). An improved feature selection method was adopted to enhance the discriminative power of the selected features. The two-stage hybrid framework made the proposed method effective for sentiment classification of Chinese micro-blogs. Experiments on the COAE2014(Chinese Opinion Analysis Evaluation 2014) dataset show that the proposed method outperforms other schemes.

Investigating User Ridership Sentiments for Bike Sharing Programs

Bike sharing is considered a state-of-the-art transportation program. It is ideal for short or medium trips providing riders the ability to pick up a bike at any self-serve bike station and return it to any bike station located within the system’s coverage area. The bike sharing programs in the United States are still very young compared to those in European countries. Washington DC was the first jurisdiction to devise a third generation bike sharing system in the US in 2008. To evaluate the popularity of a bike sharing program, a sentiment analysis of the riders’ feedback can be performed. Twitter is a great platform to understand people’s views instantly. Social media mining is, thus, gaining popularity in many research areas including transportation. Social media mining has two major advantages over conventional attitudinal survey methods—it can easily reach a large audience and it can reflect the true behavior of participants because of the anonymity social media provides. It is known that self-imposed censor is common in responding to conversational attitudinal surveys. This study performed text mining on the tweets related to a case study (Capital Bike share of Washington DC) to perform sentiment analysis or opinion mining. The results of the text mining mostly revealed higher positive sentiments towards the current system.

融合Text-CNN与注意力机制的特产小吃评论情感分析

面向特产小吃评论数据的情感分析,旨在挖掘消费者对不同特产小吃的观点和看法,从而提高特产小吃产品的销量。针对当前特产小吃评论情感分析准确率较低的问题,本文构建了特产小吃评论数据集,并提出一种融合Text-CNN(Convolutional Naural Networks)与注意力机制的模型对其进行情感分析。首先,通过Text-CNN对文本局部特征信息进行提取;然后,将局部特征引入注意力机制单元中,完成对文本信息的特征提取。最后在Softmax分类器中输入提取的特征,进行情感分类。实验结果表明,提出的模型与Text-CNN、Bi-RNN+Attention、Char-CNN、LEAM四种模型进行对比,准确率有所提升。

Sentiment Analysis of Investor Opinions on Twitter

The rapid growth of social networks has produced an unprecedented amount of user-generated data, which provides an excellent opportunity for text mining. Sentiment analysis, an important part of text mining, attempts to learn about the authors’ opinion on a text through its content and structure. Such information is particularly valuable for determining the overall opinion of a large number of people. Examples of the usefulness of this are predicting box office sales or stock prices. One of the most accessible sources of user-generated data is Twitter, which makes the majority of its user data freely available through its data access API. In this study we seek to predict a sentiment value for stock related tweets on Twitter, and demonstrate a correlation between this sentiment and the movement of a company’s stock price in a real time streaming environment. Both n-gram and “word2vec” textual representation techniques are used alongside a random forest classification algorithm to predict the sentiment of tweets. These values are then evaluated for correlation between stock prices and Twitter sentiment for that each company. There are significant correlations between price and sentiment for several individual companies. Some companies such as Microsoft and Walmart show strong positive correlation, while others such as Goldman Sachs and Cisco Systems show strong negative correlation. This suggests that consumer facing companies are affected differently than other companies. Overall this appears to be a promising field for future research.

Integrated Real-Time Big Data Stream Sentiment Analysis Service

Opinion (sentiment) analysis on big data streams from the constantly generated text streams on social media networks to hundreds of millions of online consumer reviews provides many organizations in every field with opportunities to discover valuable intelligence from the massive user generated text streams. However, the traditional content analysis frameworks are inefficient to handle the unprecedentedly big volume of unstructured text streams and the complexity of text analysis tasks for the real time opinion analysis on the big data streams. In this paper, we propose a parallel real time sentiment analysis system: Social Media Data Stream Sentiment Analysis Service (SMDSSAS) that performs multiple phases of sentiment analysis of social media text streams effectively in real time with two fully analytic opinion mining models to combat the scale of text data streams and the complexity of sentiment analysis processing on unstructured text streams. We propose two aspect based opinion mining models: Deterministic and Probabilistic sentiment models for a real time sentiment analysis on the user given topic related data streams. Experiments on the social media Twitter stream traffic captured during the pre-election weeks of the 2016 Presidential election for real-time analysis of public opinions toward two presidential candidates showed that the proposed system was able to predict correctly Donald Trump as the winner of the 2016 Presidential election. The cross validation results showed that the proposed sentiment models with the real-time streaming components in our proposed framework delivered effectively the analysis of the opinions on two presidential candidates with average 81% accuracy for the Deterministic model and 80% for the Probabilistic model, which are 1% - 22% improvements from the results of the existing literature.

基于BERT和超图对偶注意力网络的文本情感分析

针对网络短文本存在大量的噪声和缺乏上下文信息的问题,提出一种基于BERT和超图对偶注意力机制的文本情感分析模型。首先利用BERT预训练模型强大的表征学习能力,对情感文本进行动态特征提取;同时挖掘文本的上下文顺序信息、主题信息和语义依存信息将其建模成超图,通过对偶图注意力机制来对以上关联信息进行聚合;最终将BERT和超图对偶注意力网络两个模块提取出的特征进行拼接,经过softmax层得到对文本情感倾向的预测结果。该模型在电商评论二分类数据集和微博文本六分类数据集上的准确率分别达到95.49%和79.83%,相较于基准模型分别提高2.27%~3.45%和6.97%~11.69%;同时还设计了消融实验验证模型各部分对分类结果的增益。实验结果表明,该模型能够显著提高针对中文网络短文本情感分析的准确率。

基于文本挖掘的新冠肺炎疫情下医药在线消费者的需求研究

基于新冠肺炎疫情下医药电商交易规模的爆炸式增长,对医药电商在线评论进行文本分析,以某B2C医药电商平台2019—2021年在线评论数据为样本,利用LDA主题模型提取在线评论蕴含的主题,并构建情感词典融合深度学习的情感分析模型,对评论和主题词进行情感分析。研究结果显示:1)消费者网购医药商品始终关注平台的可靠性、物流服务、商品价格、药品的使用效果;2)新冠肺炎疫情爆发之前,消费者对服务态度、商品品牌、购买便捷性有很大关注度;疫情爆发后对感冒类和维生素类药品关注度更高,疫情的爆发会影响消费者的购药决策;后疫情时代,消费者更关注商品性价比、购买快捷性以及药品的品质;3)消费者对于在医药电商平台进行购药整体上表现出积极正面的情感态度;4)负面在线评论主要集中在价格、药效、处方药购买、虚假宣传、物流包装、限购等方面。本研究挖掘出疫情下消费者对于网购医药商品的需求重点和痛点,对医药电商平台改善服务质量提供建设性意见。

融合双通道特征的中文短文本情感分类模型

中文短文本具有特征稀疏、歧义多、信息不规范、文本情感丰富等特点,现有基于深度学习的中文短文本情感分类模型具有提取文本特征不充分和只注重语义信息而忽视句法信息的问题。针对上述问题提出融合双通道特征的中文短文本情感分类模型。预训练模型得到动态词向量,赋予模型更丰富的语言特征和明确的句法信息。双通道提取动态词向量的文本特征,上侧通道改进了DPCNN网络,提取文本丰富的长距离依赖关系;下侧通道建立双向长短期记忆网络各时间的字词特征和文本特征的多头自注意力关系,学习更加充分的文本特征,对分类结果较为关键的词汇给予更多的关注。将双通道的特征信息拼接获得最终的文本表示。实验结果表明,该分类模型在Chn-SentiCorp、微博评论和电商评论数据集的准确率分别能够达到96.54%、92.05%和94.3%,对比模型准确率平均值高2.28、2.44和1.01个百分点。融合双通道特征的中文短文本情感分类模型能有效提高文本分类准确率,为中文短文本情感分类提供了新的理论模型。

企业ESG与资本市场表现——来自股票流动性的证据

在经济社会发展绿色化、低碳化态势下,ESG理念在资本市场中的地位日益凸显。文章基于2015—2021年我国A股上市公司数据,研究ESG表现对企业股票流动性的影响。研究发现,ESG表现显著提升了企业股票流动性,该效应在国有企业、大规模企业以及市场化程度较高的地区企业中更显著。机制分析表明,企业ESG有利于提升投资者情绪和信息透明度,进而促进股票流动性。进一步研究发现,企业良好ESG表现所带来的股票流动性显著提升了企业价值和企业创新。发掘企业ESG在金融市场的作用效果,为活跃资本市场提供新的经验证据。

基于文本挖掘的跑鞋用户评价及情感分析

为了挖掘消费者在线购买跑鞋时的关注信息,文章用大数据分析视角,以“京东商城”为例按照销量排序分析了前600款跑鞋品牌定位、价格分布、优惠信息、标签占比,使用LDA模型对10万条跑鞋在线评论进行文本挖掘,对商品评论数据进行词频共现分析、主题聚类与情感分析,从品牌、技术和售后服务的维度分析了问题的原因并提出相关建议。研究表明:国产品牌跑鞋在各价位段布局完整,销量高的跑鞋多使用满减和商品券,自营和优惠券标签对跑鞋购买具较为显著的促进作用;消费者购买跑鞋时主要关注外观细节、功能属性、性价比、穿着感受、服务优惠等方面。

基于社交媒体数据的城市洪涝灾害信息智能提取与分析

近年来,由于气候变化导致极端降雨引起的城市内涝灾害事件频发,给我国城市水安全和可持续发展带来威胁,准确掌握受灾区域的舆论主体和公众情绪,对提高应急管理部门内涝灾害的态势感知能力具有重要意义。在当今智能网络时代,人们通过社交媒体反映问题和建议的诉求日益凸显,社交媒体已逐渐成为反映民众情感和社会舆情的主要载体,为获取自然灾害信息提供了新的途径。如何从社交媒体中快速提取城市洪涝灾害信息,并对自然灾害信息进行主题分类和情感分析,准确掌握区域灾情的主题类别和民众舆论倾向,是目前亟待解决的关键技术问题。以新浪微博为例,阐述了洪涝灾害数据的获取与预处理方法,构建了基于FastText的城市洪涝灾害信息主题分类和情感分析模型,以准确掌握受灾区域的主题类别和舆论导向。以2021年郑州“7.20”特大暴雨期间洪涝灾害为例的研究结果表明,本文方法实现了对社交媒体中城市洪涝灾害数据的智能提取与分析,主题分类模型对预设八种类别数据的分类预测F1值达到0.80以上,且情感分析模型基本能够准确预测情感标记为“负面”的数据,这表明本文构建的基于FastText的城市洪涝灾害信息主题分类和情感分析模型能够满足支撑城市应急管理部门动态掌握洪涝灾害发展态势及公众情绪的需求,对防涝减灾调度、安抚民众情绪和实时定点救援等工作具有重要的指导意义。