文本情感分类中生成式情感模型的发展

描述了生成式模型的概念及它在文本情感分类领域的发展,分析了生成式情感模型的分类,着重研究了不同生成式情感模型之间的关联性,并对生成式模型中最有代表性的三类模型进行了介绍,最后对生成式情感模型发展以及未来趋势进行了总结.     

多特征混合模型文本情感分析方法

近年来,深度学习被广泛应用于文本情感分析。其中文本卷积神经网络（TextCNN）最具代表性,但是TxetCNN的语义特征提取存在词嵌入维度语义特征丢失、最大池化算法特征提取不足和文本长期依赖关系丢失的问题。针对以上问题,提出多特征混合模型（BiLSTM-MFCNN）的文本情感分析方法。该方法使用双向长短记忆网络（BiLSTM）学习文本的长期依赖关系;改进TextCNN的卷积层和池化层提出多特征卷积神经网络（MFCNN）,卷积层利用五种不同的卷积算法,分别从句子维度、整个词嵌入维度、单个词嵌入维度、相邻词向量维度和单个词向量维度提取文本的语义特征,池化层利用最大池化算法和平均池化算法,获取文本的情感特征。在中文NLPCC Emotion Classification Challenge和COAE2014数据集、英文Twitter数据集进行对比实验,实验结果表明该混合模型在文本情感分析任务中能够取得更好的效果。     

基于情感角色模型的文本情感分类方法

针对传统情感分类方法因情感项指向不明引发的误判和隐藏观点遗漏等问题,提出一种基于评价对象情感角色模型的文本情感分类方法.该方法首先识别文本中的潜在评价对象,通过局部语义分析对潜在评价对象所在语句进行情感标注,确定潜在评价对象所在语句的正负极性,并定义其情感角色;然后,改进特征权值计算方法,将情感角色对应的倾向值融入模型特征空间中;最后,通过特征聚合对特征空间实现模型降维.实验结果表明,所提方法与提取强主观性情感项作为特征的情感分类方法相比,分类准确率约提高3.2%,可有效改善文本情感分类效果.     

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。     

融合通道特征的混合神经网络文本分类模型

基于卷积神经网络与循环神经网络的混合文本分类模型通常使用单通道词嵌入.单通道词嵌入空间维度低,特征表示单一,导致一维卷积神经网络不能充分学习文本的空间特征,影响了模型的性能.因此,该文提出一种融合通道特征的混合神经网络文本分类模型.该模型使用了双通道词嵌入丰富文本表示,增加了空间维度,在卷积的过程中融合了通道特征,优化...     

一种针对短文本的主题情感混合模型

主题情感混合模型可以同时提取语料的主题信息和情感倾向。针对短文本特征稀疏的问题,主题情感联合分析方法较少的问题,该文提出了BJSTM模型(Biterm Joint Sentiment Topic Model),在BTM模型(Biterm Topic Model)的基础上,增加情感层的设置,从而形成“情感-主题-词汇”的三层贝叶斯模型。对每个双词的情感和主题进行采样,从而对整个语料的词共现关系建模,一定程度上克服了短文本的稀疏性。实验表明,BJSTM模型在无监督情感分类和主题提取方面都有不错的表现。     

Mixed-Fisher特征云模型聚类在文本情感分类中的应用

海量网络信息的出现,使得提取文本信息情感观点成为研究的热点。针对文本情感分类中文本信息模糊及分类准确率低的问题,提出了一种基于Mixed-Fisher特征选择的文本云向量模型聚类算法。该算法首先分别计算文档中各个词性特征项的Fisher判别比,根据Fisher判别比越大特征向量判别性越强的Fisher准则,选择Fisher比值较大的前q个特征,并按照词性进行组合生成文档的Mixed-Fisher特征向量。然后在Mixed-Fisher特征向量集上构建文档的云向量模型,根据云向量模型间的差异度对模型进行聚类和合并。将该算法应用于文本情感观点的分类,选择核Fisher判别技术用于最终文本观点的判定。仿真实验结果表明,基于Mixed-Fisher特征的云向量聚类模型的分类准确率明显优于传统向量空间模型,从而验证了核Fisher判别技术的有效性。     

ELMo-CNN-BiGRU双通道文本情感分类模型

文本情感分类通过对带有情感色彩的主观性文本进行分析和推理,帮助用户更好地做出判断与决策。针对传统情感分类模型难以根据上下文信息调整词向量的问题,提出一种双通道文本情感分类模型。利用ELMo和Glove预训练模型分别生成动态和静态词向量,通过堆叠嵌入2种词向量生成输入向量。采用自注意力机制处理输入向量,计算内部的词依赖关系。构建融合卷积神经网络（CNN）和双向门控递归单元（BiGRU）的双通道神经网络结构,同时获取文本局部特征和全局特征。最终将双通道处理结果进行拼接,经过全连接层处理后输入分类器获得文本情感分类结果。实验结果表明,与同类情感分类模型中性能较优的H-BiGRU模型相比,ELMo-CNN-BiGRU模型在IMDB、yelp和sentiment140数据集上的准确率和F1值分别提升了2.42、1.98、2.52和2.40、1.94、2.43个百分点,具有更好的短文本情感分类效果和稳定性。     

Document-level sentiment classification using hybrid machine learning approach

It is a practice that users or customers intend to share their comments or reviews about any product in different social networking sites. An analyst usually processes to reviews properly to obtain any meaningful information from it. Classification of sentiments associated with reviews is one of these processing steps. The reviews framed are often made in text format. While processing the text reviews, each word of the review is considered as a feature. Thus, selection of right kind of features needs to be carried out to select the best feature from the set of all features. In this paper, the machine learning algorithm, i.e., support vector machine, is used to select the best features from the training data. These features are then given input to artificial neural network method, to process further. Different performance evaluation parameters such as precision, recall, f-measure, accuracy have been considered to evaluate the performance of the proposed approach on two different datasets, i.e., IMDb dataset and polarity dataset.     

A new hybrid feature selection approach using feature association map for supervised and unsupervised classification

Feature selection, both for supervised as well as for unsupervised classification is a relevant problem pursued by researchers for decades. There are multiple benchmark algorithms based on filter, wrapper and hybrid methods. These algorithms adopt different techniques which vary from traditional search-based techniques to more advanced nature inspired algorithm based techniques. In this paper, a hybrid feature selection algorithm using graph-based technique has been proposed. The proposed algorithm has used the concept of Feature Association Map (FAM) as an underlying foundation. It has used graph-theoretic principles of minimal vertex cover and maximal independent set to derive feature subset. This algorithm applies to both supervised and unsupervised classification. The performance of the proposed algorithm has been compared with several benchmark supervised and unsupervised feature selection algorithms and found to be better than them. Also, the proposed algorithm is less computationally expensive and hence has taken less execution time for the publicly available datasets used in the experiments, which include high-dimensional datasets.     

A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

Ensemble of feature sets and classification algorithms for sentiment classification

In this paper, we make a comparative study of the effectiveness of ensemble technique for sentiment classification. The ensemble framework is applied to sentiment classification tasks, with the aim of efficiently integrating different feature sets and classification algorithms to synthesize a more accurate classification procedure. First, two types of feature sets are designed for sentiment classification, namely the part-of-speech based feature sets and the word-relation based feature sets. Second, three well-known text classification algorithms, namely na?¨ve Bayes, maximum entropy and support vector machines, are employed as base-classifiers for each of the feature sets. Third, three types of ensemble methods, namely the fixed combination, weighted combination and meta-classifier combination, are evaluated for three ensemble strategies. A wide range of comparative experiments are conducted on five widely-used datasets in sentiment classification. Finally, some in-depth discussion is presented and conclusions are drawn about the effectiveness of ensemble technique for sentiment classification.     

情境特征及其在情感分类模型中的应用

研究情境特征在文本分类中的作用,提出了一种层级双向LSTM模型用于情感分类问题。该模型首先将句子分词,把词向量作为第一层双向LSTM模型的输入;其次从文档中提取出稠密、连续的向量作为情境特征;然后将第一层模型的输出向量和情境向量共同输入第二层双向LSTM;最后将这种层级双向的LSTM模型的输出向量通过sigmoid函数进行分类。情境向量作用于每个句子,一致的情感得到增强,不一致的情感被弱化,从而提高了分类的精度。在两个公开数据集上的实验表明,整合了情境特征的层级双向LSTM取得较优的精度。除此之外,通过在一个包含两万余条中文评论的公开数据集上对模型进行测试,表明该模型测试正确率相比于普通的LSTM和双向LSTM都有提升,说明情境特征对于提升情感分类的作用比较显著。     

Particle swarm optimization-based feature selection in sentiment classification

Sentiment classification is one of the important tasks in text mining, which is to classify documents according to their opinion or sentiment. Documents in sentiment classification can be represented in the form of feature vectors, which are employed by machine learning algorithms to perform classification. For the feature vectors, the feature selection process is necessary. In this paper, we will propose a feature selection method called fitness proportionate selection binary particle swarm optimization (F-BPSO). Binary particle swarm optimization (BPSO) is the binary version of particle swam optimization and can be applied to feature selection domain. F-BPSO is a modification of BPSO and can overcome the problems of traditional BPSO including unreasonable update formula of velocity and lack of evaluation on every single feature. Then, some detailed changes are made on the original F-BPSO including using fitness sum instead of average fitness in the fitness proportionate selection step. The modified method is, thus, called fitness sum proportionate selection binary particle swarm optimization (FS-BPSO). Moreover, further modifications are made on the FS-BPSO method to make it more suitable for sentiment classification-oriented feature selection domain. The modified method is named as SCO-FS-BPSO where SCO stands for “sentiment classification-oriented”. Experimental results show that in benchmark datasets original F-BPSO is superior to traditional BPSO in feature selection performance and FS-BPSO outperforms original F-BPSO. Besides, in sentiment classification domain, SCO-FS-BPSO which is modified specially for sentiment classification is superior to traditional feature selection methods on subjective consumer review datasets.     

A hybrid neural network/genetic algorithm approach to optimizing feature extraction for signal classification.

In this paper, a hybrid neural network/genetic algorithm technique is presented, aiming at designing a feature extractor that leads to highly separable classes in the feature space. The application upon which the system is built, is the identification of the state of human peripheral vascular tissue (i.e., normal, fibrous and calcified). The system is further tested on the classification of spectra measured from the cell nucleii in blood samples in order to distinguish normal cells from those affected by Acute Lymphoblastic Leukemia. As advantages of the proposed technique we may encounter the algorithmic nature of the design procedure, the optimized classification results and the fact that the system performance is less dependent on the classifier type to be used.     

A hybrid approach to feature segmentation of triangle meshes

Segmentation of a polygonal mesh is a method of breaking the mesh down into ‘meaningful’ connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9] and [10]. Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops.We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.     

维吾尔文情感分类特征建设研究

由于目前缺乏维吾尔文情感分类特征表示方面的系统性研究,以传统◢n◣-gram特征为基础,按不同规模从维吾尔文情感标注语料库中提取了新特征及其组合特征,基于支持向量机（SVM）分类器对维吾尔文情感语料库进行了正负情感分类。实验结果表明,所提取的基本特征中unigram特征的分类效率最佳;unigram特征与词组特征的组合可以进一步提高分类效率,其最佳分类效果比unigram特征的分类效果提高了1.78%。首次在统一标注数据集上对不同特征的分类性能进行了综合评价,研究成果可以为今后的维吾尔文情感分类研究提供指导。     

Successes and challenges in developing a hybrid approach to sentiment analysis

This article covers some success and learning experiences attained during the developing of a hybrid approach to Sentiment Analysis (SA) based on a Sentiment Lexicon, Semantic Rules, Negation Handling, Ambiguity Management and Linguistic Variables. The proposed hybrid method is presented and applied to two selected datasets: Movie Review and Sentiment Twitter datasets. The achieved results are compared against those obtained when Naïve Bayes (NB) and Maximum Entropy (ME) supervised machine learning classification methods are used for the same datasets. The proposed hybrid system attained higher accuracy and precision scores than NB and ME, which shows its superiority when applied to the SA problem at the sentence level. Finally, an alternative strategy to calculating the orientation polarity and polarity intensity in one step instead of the two steps method used in the hybrid approach is explored. The analysis of the yielded mixed results achieved with this alternative approach shows its potential as an aid in the computation of semantic orientations and produced some lessons learnt in developing a more effective mechanism to calculating the orientation polarity and polarity intensity.