Approach For Sentiment Classification Research Articles

A Combination of Query Expansion Ranking and GA-SVM for Improving Indonesian Sentiment Classification Performance

The sentiment classification method is a research field that is proliferating in Indonesia since it is fast in extracting public opinion and provides essential and valuable information for stakeholders. Of the best-performing sentiment classification approaches, machine learning is one of them that has excellent performance. However, the method has several problems, such as noisy features and high dimensionality of features that significantly affect the sentiment classification performance. Therefore, to overcome the problems, this paper presents a novel feature selection using a combination of Query Expansion Ranking (QER) and Genetic Algorithm-Support Vector Machine (GA-SVM) for improving sentiment classification performance. Based on the experimental results, the proposed method could significantly improve sentiment classification performance, outperform all state-of-the-art algorithms, and decrease computational time. The method achieved the best performance in average precision, recall, and f-measure with the value of 96.78%, 96.76%, and 96.75%, respectively.

A Hybrid Deep Learning Model for Long-Term Sentiment Classification

With the omnipresence of user feedbacks in social media, mining of relevant opinion and extracting the underlying sentiment to analyze synthetic emotion towards a specific product, person, topic or event has become a vast domain of research in recent times. A thorough survey of the early unimodal and multimodal sentiment classification approaches reveals that researchers mostly relied on either corpus based techniques or those based on machine learning algorithms. Lately, Deep learning models progressed profoundly in the area of image processing. This success has been efficiently directed towards enhancements in sentiment categorization. A hybrid deep learning model consisting of Convolutional Neural Network (CNN) and stacked bidirectional Long Short Term Memory (BiLSTM) over pre-trained word vectors is proposed in this paper to achieve long-term sentiment analysis. This work experiments with various hyperparameters and optimization techniques to make the model get rid of overfitting and to achieve optimal performance. It has been validated on two standard sentiment datasets, Stanford Large Movie Review (IMDB) and Stanford Sentiment Treebank2 Dataset (SST2). It achieves a competitive advantage over other models like CNN, LSTM and ensemble of CNN-LSTM by attaining better accuracy and also produces high F measure.

Collaborative attention neural network for multi-domain sentiment classification

Multi-domain sentiment classification is a challenging topic in natural language processing, where data from multiple domains are applied to improve the performance of classification. Recently, it has been demonstrated that attention neural networks exhibit powerful performance in this task. In the present study, we propose a collaborative attention neural network (CAN). A self-attention module and domain attention module work together in our approach, where the hidden states generated in the self-attention module are fed into both the domain sub-module and sentiment sub-module in the domain attention module. Compared with other attention neural networks, we use two types of attention modules to conduct the auxiliary and main sentiment classification tasks. The experimental results showed that CAN outperforms other state-of-the-art sentiment classification approaches in terms of the overall accuracy based on both English (Amazon) and Chinese (JD) multi-domain sentiment analysis data sets.

Sentiment Analysis for Arabic Social Media

With the spread of social media services in Arabic societies, it leads to the explosive growth of Arabic posts, or comments. These services generate a huge volume of opinionated data on different topics such as politics and businesses. Analyzing valuable subjective information from data would assist in a better understanding and making decisions. Therefore, sentiment analysis coincides with social media networks and has become the most interesting research field in the sentiment analysis process. However, there are several challenges faced the sentiment analysis process. Arabic Sentiment analysis is indeed in its infantile stage and it has not obtained thoroughly attention wherein several challenges still need to address. Some of these challenges result from the complexity of Arabic natural language and other challenges result from social media platform itself. In this manuscript, we first study the impact of social media challenges on the challenges of Arabic language. Our findings show that such challenges add more complexities to the sentiment analysis process. Based on these findings, we review the contributed proposals, which give rise on analyzing Arabic social media data. Our review methodology is based on a set of criteria, which we propose to assess the advantages and limitations of these proposals. The interesting point here is to help researchers identify the social sentiment analysis problems along with a comprehensive survey on the sentiment analysis levels and classification approaches. Finally, we compare these proposals in terms of the average accuracy and suggest a new hybrid approach based on our findings.

SSAAR: An enhanced System for Sentiment Analysis of Arabic Reviews

Sentiment Analysis, or Opinion Mining, has recently captivated the interest of scientists worldwide. With the increasing use of the internet, the web is becoming overloaded by data that contains useful information, which can be used in different fields. In fact, many studies have shed light on Sentiment Analysis of online data in different languages. However, the amount of research dealing with the Arabic language is still limited. In this paper, an empirical study is led to Sentiment Analysis of online reviews written in Modern Standard Arabic. A new system called SSAAR (System for Sentiment Analysis of Arabic Reviews) is proposed, allowing computational classification of reviews into three classes (positive, negative, neutral). The input data of this system is built by using a proposed framework called SPPARF (Scraping and double Preprocessing Arabic Reviews Framework), which generates a structured and clean dataset. Moreover, the provided system experiments two improved approaches for sentiment classification based on supervised learning, which are: Double preprocessing method and Feature selection method. Both approaches are trained by using five algorithms (Naïve Bayes, stochastic gradient descent Classifier (SGD), Logistic Regression, K-Nearest Neighbors, and Random Forest) and compared later under the same conditions. The experimental results show that the feature selection method using the SGD Classifier performs the best accuracy (77.1%). Therefore, the SSAAR System proved to be efficient and gives better results when using the feature selection method; nevertheless, satisfying results were obtained with the other approach, considered consequently suitable for the proposed system.

Domain-specific sentiment analysis for tweets during hurricanes (DSSA-H): A domain-adversarial neural-network-based approach

Hurricanes are one of the most frequent and destructive disasters in the United States. The events are large scale and have relatively long-term impacts. Social networking platforms such as Twitter can provide real-time information for disaster managers and affected populations during large-scale disasters (e.g., hurricanes), but extracting useful information and interpreting data accurately for disaster management is still challenging. Sentiment analysis of social media data helps detect the concerns of affected people and understand individuals' responses on the ground at unprecedented scales, but the method is known to be domain-dependent. The same words or expressions can indicate opposite sentiments in different domains. This paper proposes a domain-specific sentiment analysis approach specifically for tweets posted during hurricanes (DSSA-H). DSSA-H can retrieve hurricane-relevant tweets with a trained supervised-learning classifier, Random Forest (RF), and classify the sentiment of hurricane-relevant tweets based on a domain-adversarial neural network (DANN). We built a dataset of tweets posted during six recent hurricanes and applied the DSSA-H approach for sentiment analysis. After evaluation, we found that each classifier (i.e., RF and DANN) outperforms baseline classifiers and that DSSA-H outperforms two high-performing general sentiment classification approaches when classifying sentiments of tweets posted during hurricanes. We also applied DSSA-H in examining sentiment patterns across six recent hurricanes in the U.S. This domain-specific sentiment analysis approach can be used by the first responders and affected communities to more accurately and rapidly detect crises and emergent events, allocate resources, and assess disaster's impact during hurricanes. DSSA-H contributes to an intelligent and adaptive disaster information system for the data-rich human and the built environment system.

Lifelong Machine Learning Architecture for Classification

Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is isolated with others. Although open source datasets are available, algorithms’ performance is asymmetric with the data volume. Hence, the AI community wishes to raise a symmetric continuous learning architecture which can automatically learn and adapt to different tasks. Such a learning architecture also is commonly called as lifelong machine learning (LML). This learning paradigm could manage the learning process and accumulate meta-knowledge by itself during learning different tasks. The meta-knowledge is shared among all tasks symmetrically to help them to improve performance. With the growth of meta-knowledge, the performance of each task is expected to be better and better. In order to demonstrate the application of lifelong machine learning, this paper proposed a novel and symmetric lifelong learning approach for sentiment classification as an example to show how it adapts different domains and keeps efficiency meanwhile.

Multi-Source Domain Adaptation for Visual Sentiment Classification

Existing domain adaptation methods on visual sentiment classification typically are investigated under the single-source scenario, where the knowledge learned from a source domain of sufficient labeled data is transferred to the target domain of loosely labeled or unlabeled data. However, in practice, data from a single source domain usually have a limited volume and can hardly cover the characteristics of the target domain. In this paper, we propose a novel multi-source domain adaptation (MDA) method, termed Multi-source Sentiment Generative Adversarial Network (MSGAN), for visual sentiment classification. To handle data from multiple source domains, it learns to find a unified sentiment latent space where data from both the source and target domains share a similar distribution. This is achieved via cycle consistent adversarial learning in an end-to-end manner. Extensive experiments conducted on four benchmark datasets demonstrate that MSGAN significantly outperforms the state-of-the-art MDA approaches for visual sentiment classification.

Deep Learning-Based Sentiment Classification: A Comparative Survey

Recently, Deep Learning (DL) approaches have been applied to solve the Sentiment Classification (SC) problem, which is a core task in reviews mining or Sentiment Analysis (SA). The performances of these approaches are affected by different factors. This paper addresses these factors and classifies them into three categories: data preparation based factors, feature representation based factors and the classification techniques based factors. The paper is a comprehensive literature-based survey that compares the performance of more than 100 DL-based SC approaches by using 21 public datasets of reviews given by customers within three specific application domains (products, movies and restaurants). These 21 datasets have different characteristics (balanced/imbalanced, size, etc.) to give a global vision for our study. The comparison explains how the proposed factors quantitatively affect the performance of the studied DL-based SC approaches.

LeSSA: A Unified Framework based on Lexicons and Semi-Supervised Learning Approaches for Textual Sentiment Classification

Sentiment Analysis (SA) is an active research area. SA aims to classify the online unstructured user-generated contents (UUGC) into positive and negative classes. A reliable training data is vital to learn a sentiment classifier for textual sentiment classification, but due to domain heterogeneity, manually construction of reliable labeled sentiment corpora is a laborious and time-consuming task. In the absence of enough labeled data, the alternative usage of sentiment lexicons and semi-supervised learning approaches for sentiment classification have substantially attracted the attention of the research community. However, state-of-the-art techniques for semi-supervised sentiment classification present research challenges expressed in questions like the following. How to effectively utilize the concealed significant information in the unstructured data? How to learn the model while considering the most effective sentiment features? How to remove the noise and redundant features? How to refine the initial training data for initial model learning as the random selection may lead to performance degradation? Besides, mainly existing lexicons have trouble with word coverage, which may ignore key domain-specific sentiment words. Further research is required to improve the sentiment lexicons for textual sentiment classification. In order to address such research issues, in this paper, we propose a novel unified sentiment analysis framework for textual sentiment classification called LeSSA. Our main contributions are threefold. (a) lexicon construction, generating quality and wide coverage sentiment lexicon. (b) training classification models based on a high-quality training dataset generated by using k-mean clustering, active learning, self-learning, and co-training algorithms. (c) classification fusion, whereby the predictions from numerous learners are confluences to determine final sentiment polarity based on majority voting, and (d) practicality, that is, we validate our claim while applying our model on benchmark datasets. The empirical evaluation of multiple domain benchmark datasets demonstrates that the proposed framework outperforms existing semi-supervised learning techniques in terms of classification accuracy.

Sentiment classification of Chinese cosmetic reviews based on integration of collocations and concepts

PurposeThis paper aims to propose a novel approach which integrates collocations and domain concepts for Chinese cosmetic word of mouth (WOM) sentiment classification. Most sentiment analysis works by collecting sentiment scores from each unigram or bigram. However, not every unigram or bigram in a WOM document contains sentiments. Chinese collocations consist of the main sentiments of WOM. This paper reduces the complexity of the document dimensionality and makes an improvement for sentiment classification.Design/methodology/approachThis paper builds two contextual lexicons for feature words and sentiment words, respectively. Based on these contextual lexicons, this paper uses the techniques of associated rules and mutual information to build possible Chinese collocation sets. This paper applies preference vector modelling as the vector representation approach to catch the relationship between Chinese collocations and their associated concepts.FindingsThis paper compares the proposed preference vector models with benchmarks, using three classification techniques (i.e. support vector machine, J48 decision tree and multilayer perceptron). According to the experimental results, the proposed models outperform all benchmarks evaluated by the criterion of accuracy.Originality/valueThis paper focuses on Chinese collocations and proposes a novel research approach for sentiment classification. The Chinese collocations used in this paper are adaptable to the content and domains. Finally, this paper integrates collocations with the preference vector modelling approach, which not only achieves a better sentiment classification performance for Chinese WOM documents but also avoids the curse of dimensionality.

Kernel Optimized-Support Vector Machine and MapReduce Framework for Sentiment Classification of Train Reviews

Sentiment analysis is one of the popular techniques gaining attention in recent times. Nowadays, people gain information on reviews of users regarding public transportation, movies, hotel reservation, etc., by utilizing the resources available, as they meet their needs. Hence, sentiment classification is an essential process employed to determine the positive and negative responses. This paper presents an approach for sentiment classification of train reviews using MapReduce model with the proposed Kernel Optimized-Support Vector Machine (KO-SVM) classifier. The MapReduce framework handles big data using a mapper, which performs feature extraction and reducer that classifies the review based on KO-SVM classification. The feature extraction process utilizes features that are classification-specific and SentiWordNet-based. KO-SVM adopts SVM for the classification, where the exponential kernel is replaced by an optimized kernel, finding the weights using a novel optimizer, Self-adaptive Lion Algorithm (SLA). In a comparative analysis, the performance of KO-SVM classifier is compared with SentiWordNet, NB, NN, and LSVM, using the evaluation metrics, specificity, sensitivity, and accuracy, with train review and movie review database. The proposed KO-SVM classifier could attain maximum sensitivity of 93.46% and 91.249% specificity of 74.485% and 70.018%; and accuracy of 84.341% and 79.611% respectively, for train review and movie review databases.

An LSTM-CNN attention approach for aspect-level sentiment classification

An LSTM-CNN attention approach for aspect-level sentiment classification

Sentiment analysis for online reviews using conditional random fields and support vector machines

Sentiment analysis of online reviews is an important way of mining useful information from the Internet. Despite several advantages, the accuracy of sentiment analysis based on a domain dictionary relies on the comprehensiveness and accuracy of the dictionary. Instead of creating a domain dictionary, we propose an approach for online review sentiment classification, which uses a conditional random field algorithm to extract the emotional characteristics from fragments of the review. The characteristic (feature) words are then weighted asymmetrically before a support vector machine classifier is used to obtain the sentiment orientation of the review. In our experiments, the average accuracy reached 90%, showing that using sentiment feature fragments instead of whole reviews and weighting the characteristic words asymmetrically can improve the sentiment classification accuracy.

Cross-D-vectorizers: a set of feature-spaces for cross-domain sentiment analysis from consumer review

Supervised sentiment classification approaches require labeled training (source) and testing (target) dataset. Generation of such datasets demands substantial time and effort but cross-domain classification minimizes the effort by considering two different domains for source and target datasets. In this paper, we propose Cross-D-Vectorizers i.e., a set of three sentiment n-gram feature-spaces (Lexical-TFIDF, Lex-Delta-TFIDF and SEND) for the purpose of cross-domain analysis. We construct the features by extracting sentiment unigrams combination with intensifiers and negations from the source dataset. By utilizing an existing lexicon the scores of these features are computed in three different procedures. The scores for each feature are computed by multiplying sentiment value with corresponding TFIDF rating, Delta-TFIDF rating and feature-importance-values (FIV) respectively. Importance-value for each SEND (Sentiment wEight ofN-grams inDataset) feature is calculated by multiplying the number of times the feature appears in the review and the logarithm of its inverse frequency in the corpus. We experiment by using Maximum Entropy, Support Vector Machine and K-Nearest Neighbors classifiers on three benchmark datasets and one proposed dataset for cross-domain classification. Proposed approach show improved results in comparison with existing methods. The advantage of our approach is the complexity of system reduces by considering sentiment n-grams as domain independent features instead of any n-grams.

An Improved Approach for Text Sentiment Classification Based on a Deep Neural Network via a Sentiment Attention Mechanism

Text sentiment analysis is an important but challenging task. Remarkable success has been achieved along with the wide application of deep learning methods, but deep learning methods dealing with text sentiment classification tasks cannot fully exploit sentiment linguistic knowledge, which hinders the development of text sentiment analysis. In this paper, we propose a sentiment-feature-enhanced deep neural network (SDNN) to address the problem by integrating sentiment linguistic knowledge into a deep neural network via a sentiment attention mechanism. Specifically, first we introduce a novel sentiment attention mechanism to help select the crucial sentiment-word-relevant context words by leveraging the sentiment lexicon in an attention mechanism, which bridges the gap between traditional sentiment linguistic knowledge and current popular deep learning methods. Second, we develop an improved deep neural network to extract sequential correlation information and text local features by combining bidirectional gated recurrent units with a convolutional neural network, which further enhances the ability of comprehensive text representation learning. With this design, the SDNN model can generate a powerful semantic representation of text to improve the performance of text sentiment classification tasks. Extensive experiments were conducted to evaluate the effectiveness of the proposed SDNN model on two real-world datasets with a binary-sentiment-label and a multi-sentiment-label. The experimental results demonstrated that the SDNN achieved substantially better performance than the strong competitors for text sentiment classification tasks.

Anomaly analysis based on meta-subspace approach for sentiment classification

Anomaly analysis based on meta-subspace approach for sentiment classification

Transportation sentiment analysis using word embedding and ontology-based topic modeling

Social networks play a key role in providing a new approach to collecting information regarding mobility and transportation services. To study this information, sentiment analysis can make decent observations to support intelligent transportation systems (ITSs) in examining traffic control and management systems. However, sentiment analysis faces technical challenges: extracting meaningful information from social network platforms, and the transformation of extracted data into valuable information. In addition, accurate topic modeling and document representation are other challenging tasks in sentiment analysis. We propose an ontology and latent Dirichlet allocation (OLDA)-based topic modeling and word embedding approach for sentiment classification. The proposed system retrieves transportation content from social networks, removes irrelevant content to extract meaningful information, and generates topics and features from extracted data using OLDA. It also represents documents using word embedding techniques, and then employs lexicon-based approaches to enhance the accuracy of the word embedding model. The proposed ontology and the intelligent model are developed using Web Ontology Language and Java, respectively. Machine learning classifiers are used to evaluate the proposed word embedding system. The method achieves accuracy of 93%, which shows that the proposed approach is effective for sentiment classification.

Unsupervised Multi-class Sentiment Classification Approach

Unsupervised Multi-class Sentiment Classification Approach

Kernel Optimized-Support Vector Machine and Mapreduce framework for sentiment classification of train reviews

Sentiment analysis is one of the popular techniques gaining attention in recent times. Nowadays, people gain information on reviews of users regarding public transportation, movies, hotel reservation, etc., by utilizing the resources available, as they meet their needs. Hence, sentiment classification is an essential process employed to determine the positive and negative responses. This paper presents an approach for sentiment classification of train reviews using MapReduce model with the proposed Kernel Optimized-Support Vector Machine (KO-SVM) classifier. The MapReduce framework handles big data using a mapper, which performs feature extraction and reducer that classifies the review based on KO-SVM classification. The feature extraction process utilizes features that are classification-specific and SentiWordNet-based. KO-SVM adopts SVM for the classification, where the exponential kernel is replaced by an optimized kernel, finding the weights using a novel optimizer, self-adaptive lion algorithm. In a comparative analysis, the performance of KO-SVM classifier is compared with SentiWordNet, Naive Bayes, neural network, and LSVM, using the evaluation metrics, specificity, sensitivity, and accuracy, with train review and movie review database. The proposed KO-SVM classifier could attain maximum sensitivity of 93.46% and 91.249%, specificity of 74.485% and 70.018%; and accuracy of 84.341% and 79.611%, respectively, for train review and movie review databases.