Local dense mixed region cutting + global rebalancing: a method for imbalanced text sentiment classification

ABSTRACTWith diverse online media emerging, there is a growing concern of sentiment classification problem. At present, text sentiment classification mainly utilizes supervised machine learning methods, which feature certain domain dependency. On the basis of Markov logic networks (MLNs), this study proposed a cross-domain multi-task text sentiment classification method rooted in transfer learning. Through many-to-one knowledge transfer, labeled text sentiment classification, knowledge was successfully transferred into other domains, and the precision of the sentiment classification analysis in the text tendency domain was improved. The experimental results revealed the following: (1) the model based on a MLN demonstrated higher precision than the single individual learning plan model. (2) Multi-task transfer learning based on Markov logical networks could acquire more knowledge than self-domain learning. The cross-domain text sentiment classification model could significantly improve the precision and efficiency of text sentiment classification.

Support Vector Machine and Naive Bayes are popular classification algorithms in PDF malware detection, Spam filtering and scientific community training datasets. These algorithms incorporated classifications into the training datasets which they affected with the type of causative and evasion attack. The adversaries are insect the training dataset by injecting malicious sample data. This infected training datasets are used in the ML algorithms without knowing that they are infected for research purpose. Intelligent attackers mislead the SVM and NB learning algorithms functional task by modifying the training dataset. This may cause the security problems in the training dataset. To develop security mechanism, use to cope the attack on training dataset and avoid to decreases ML algorithms performance. This paper shows that the SVM and NB accuracy reduces dramatically when they used infected training dataset. The proposed defence method Rand Check used to prevent the trusted training dataset from causative and evasion attacks.

Aiming at the problem that traditional convolutional neural networks cannot fully capture text features during feature extraction, and a single model cannot effectively extract deep text features, this paper proposes a text sentiment classification method based on the attention mechanism of LSTM-TCN hybrid model. First, use the Word2vec word vector model to transform words into the form of word vectors. Secondly, with Long Short-Term Memory (LSTM) to obtain the serialized feature information of the text, and then combined with the Temporal Convolutional Network (TCN) to sample and calculate the text features to extract more comprehensive feature information of the text. Then, combined with the attention mechanism, the influence of important information on the sentiment of the text is considered, and the effect of text sentiment classification is optimized. Finally, use softmax function to classify sentiment in the text classification layer. Multiple sets of comparative experiments were conducted on two sets of Chinese data sets, and the accuracy of the text model reached 93.06% and 91.08%, respectively, proving that the proposed model performs better than the traditional single convolutional neural network.

PurposeThis study aims to investigate the current state of research using deep learning methods for text classification in the tourism and hospitality field and to propose specific guidelines for future research.Design/methodology/approachThis study undertakes a qualitative and critical review of studies that use deep learning methods for text classification in research fields of tourism and hospitality and computer science. The data was collected from the Web of Science database and included studies published until February 2022.FindingsFindings show that current research has mainly focused on text feature classification, text rating classification and text sentiment classification. Most of the deep learning methods used are relatively old, proposed in the 20th century, including feed-forward neural networks and artificial neural networks, among others. Deep learning algorithms proposed in recent years in the field of computer science with better classification performance have not been introduced to tourism and hospitality for large-scale dissemination and use. In addition, most of the data the studies used were from publicly available rating data sets; only two studies manually annotated data collected from online tourism websites.Practical implicationsThe applications of deep learning algorithms and data in the tourism and hospitality field are discussed, laying the foundation for future text mining research. The findings also hold implications for managers regarding the use of deep learning in tourism and hospitality. Researchers and practitioners can use methodological frameworks and recommendations proposed in this study to perform more effective classifications such as for quality assessment or service feature extraction purposes.Originality/valueThe paper provides an integrative review of research in text classification using deep learning methods in the tourism and hospitality field, points out newer deep learning methods that are suitable for classification and identifies how to develop different annotated data sets applicable to the field. Furthermore, foundations and directions for future text classification research are set.

The research on text sentiment classification has been very popular. The main methods include the methods based on rules and lexicons, machine statistical learning, and neural network methods. These methods have achieved great success in text sentiment classification, but there are still many defects. For traditional methods, its versatility is poor, once the text style or format changes significantly, the rules need to be re-established. Although the neural network method is generally applicable, it is not sufficient for the application of language knowledge. In order to solve the above problems, we propose a new model combining the traditional method and neural network method. It combines transition lexicon, stacked BILSTM and attention mechanism, and uses word2vec to initialize word vectors. For sentiment classification, semantic features are necessary, stacked BILSTM can capture contextual semantics multiple times to obtain richer contextual information representation. At the same time, we consider that the polarity of the clauses before and after the transition words may be completely opposite, which will also have a significant impact on the classification results. Therefore, we propose two strategies for transition words. One is to use the transition lexicon to supervise the attention mechanism and make the attention model sensitive to the transition words. The other is to cut the sentence according to the transition words to eliminate the noise of irrelevant items in the sentence. Our method combines the advantages of traditional methods and neural network methods, and makes up for their respective shortcomings. We use the proposed method to conduct a sentimental binary classification experiment on three data sets. The experimental results show that our method is superior than the previous methods.

The process of extracting meaningful rules from big and complex data is called data mining. Data mining has an increasing popularity in every field today. Data units are established in customer-oriented industries such as marketing, finance and telecommunication to work on the customer churn and acquisition, in particular. Among the data mining methods, classification algorithms are used in studies conducted for customer acquisition to predict the potential customers of the company in question in the related industry. In this study, bank marketing data set in UCI Machine Learning Data Set was used by creating models with the same classification algorithms in different data mining programs. Accuracy, precision and f- measure criteria were used to test performances of the classification models. When creating the classification models, the test and training data sets were randomly divided by the holdout method to evaluate the performance of the data set. The data set was divided into training and test data sets with the 60-40%, 75­25% and 80-20% separation ratios. Data mining programs used for these processes are the R, Knime, RapidMiner and WEKA. And, classification algorithms commonly used in these platforms are the k-nearest neighbor (k-nn), Naive Bayes, and C4.5 decision tree.

This focus issue of Physiological Measurement follows the 38th Annual International Computing in Cardiology (CinC) Conference, hosted in Hangzhou, China in September 2011 by Zhejiang University. Each year, the NIH-sponsored PhysioNet resource (http://physionet.org/) runs an open competition lasting several months, aimed at encouraging the development of solutions to an unsolved or poorly solved problem in biomedicine, in most cases making use of relevant clinical and experimental data provided freely by PhysioNet. Participants in these annual challenges discuss their diverse approaches to the Challenge problems during dedicated scientific sessions at CinC. The topics of these PhysioNet/CinC Challenges range from physiologic signal processing and analysis to forecasting and modelling clinically important events and processes.

The effects of data preprocessing in the determination of coagulant dosing rate

IFN-signaling gene (ISG) expression scores are potential markers of inflammation with significance from cancer to genetic syndromes. In Aicardi Goutières Syndrome (AGS), a disorder of abnormal DNA and RNA metabolism, this score has potential as a diagnostic biomarker, although the approach to ISG calculation has not been standardized or validated. To optimize ISG calculation and validate ISG as a diagnostic biomarker, mRNA levels of 36 type I IFN response genes were quantified from 997 samples (including 334 AGS), and samples were randomized into training and test data sets. An independent validation cohort (n = 122) was also collected. ISGs were calculated using all potential combinations up to 6 genes. A 4-gene approach (IFI44L, IFI27, USP18, IFI6) was the best-performing model (AUC of 0.8872 [training data set], 0.9245 [test data set]). The majority of top-performing gene combinations included IFI44L. Performance of IFI44L alone was 0.8762 (training data set) and 0.9580 (test data set) by AUC. The top approaches were able to discriminate individuals with genetic interferonopathy from control samples. This study validates the context of use for the ISG score as a diagnostic biomarker and underscores the importance of IFI44L in diagnosis of genetic interferonopathies.

Three Biomarker Panel at Day 7 and 14 Can Predict Development of Grade II-IV Acute Graft-Versus-Host Disease

Supervised learning methods are widely used in text sentiment classification. To acquire high classification performance, the effective and precise term weighting scheme plays a prime and necessary role for classification system. The traditional term weighting schemes often ignore the use of the available labeling information as the prior knowledge, which results the expressed relationships between features and class labels are not accurate and adequate enough. Hence, this paper proposes a term weighting scheme which makes use of class contribution of feature terms, and obtains a scheme which takes into account the class contribution, local distribution and global distribution of feature terms. The scheme expresses the relationships between features and class labels as a class contribution degree factor which is based on posterior probability, then combines it with the factors of frequency and inverse document frequency. Compared with a series of term weighting schemes, experimental results on a widely used dataset show that the proposed scheme can significantly improve the performance of sentiment classification.

Machine learning (ML) algorithms seek to extract the most beneficial information out of the raw data. As mentioned in previous chapters, preprocess data preparation actions might be needed in order to make the data set ready to be fed into the ML algorithms. ML algorithms have gotten the attention of researchers all over the world during the last few decades. In traditional algorithms, the analyst had to define the rules, which was not always accessible or easily possible, in order to obtain the output. ML algorithms develop the models or rules based on the training data set which include input and output data points. ML algorithms try to understand more beneficial information regarding the system based on the training data set. The built model can be tested using the verification data set which does not have any overlap with the training sets. If the model acquires the acceptable performance measures, it can be applied for other cases to perform the prediction process. It should be considered that ML algorithms are not supposed to do the magic. Indeed, they are supposed to explore and analyze the training data, which the human brain is not able to handle that, to develop a predictive model in which its performance is acceptable for the verification data set. Predictive models should be generalized which means performing satisfactorily for both training and verifying data sets.

The Venturi flow meters that are being used to measure the feedwater flow rate in most pressurized water reactors are confronted with fouling phenomena, resulting in an overestimation of the flow rate. In this paper, we will therefore develop two soft-sensing models based on a fuzzy inference system and support vector regression for online prediction of the feedwater flow rate. The data-based models are developed using a training data set and a verification data set, and validated using an independent test data set. These data sets are divided from the startup data of Yonggwang Nuclear Power Plant Unit 3. The data for training the data-based models is selected with the aid of a subtractive clustering scheme because informative data increases the learning effect. The uncertainty of the data-based models is analyzed using 100 sampled training and verification data sets, and a fixed test data set. The prediction intervals are very small, which means that the predicted values are very accurate. The root mean square error and relative maximum error of the models were quite small. Also, the residual signal between the measured value and the estimated value is used to determine the overmeasure due to the fouling phenomena by a sequential probability ratio test which consequently monitors the existing feedwater flow meters.

The role of pertinently diversified and balanced training as well as testing data sets in achieving the true performance of classifiers in predicting the antifreeze proteins

Lithology prediction by support vector classifiers using inverted seismic attributes data and petrophysical logs as a new approach and investigation of training data set size effect on its performance in a heterogeneous carbonate reservoir