scholarly journals Aspect-Level Sentiment Analysis Based on Position Features Using Multilevel Interactive Bidirectional GRU and Attention Mechanism

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Xiaodi Wang ◽  
Xiaoliang Chen ◽  
Mingwei Tang ◽  
Tian Yang ◽  
Zhen Wang
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Network Models ◽  
Attention Mechanism ◽  
Sentiment Classification ◽  
Classification Model ◽  
Neural Network Models ◽  
Position Information ◽  
Gated Recurrent Unit ◽  
Relative Position Information

The aim of aspect-level sentiment analysis is to identify the sentiment polarity of a given target term in sentences. Existing neural network models provide a useful account of how to judge the polarity. However, context relative position information for the target terms is adversely ignored under the limitation of training datasets. Considering position features between words into the models can improve the accuracy of sentiment classification. Hence, this study proposes an improved classification model by combining multilevel interactive bidirectional Gated Recurrent Unit (GRU), attention mechanisms, and position features (MI-biGRU). Firstly, the position features of words in a sentence are initialized to enrich word embedding. Secondly, the approach extracts the features of target terms and context by using a well-constructed multilevel interactive bidirectional neural network. Thirdly, an attention mechanism is introduced so that the model can pay greater attention to those words that are important for sentiment analysis. Finally, four classic sentiment classification datasets are used to deal with aspect-level tasks. Experimental results indicate that there is a correlation between the multilevel interactive attention network and the position features. MI-biGRU can obviously improve the performance of classification.

Gated Hierarchical LSTMs for Target-Based Sentiment Analysis

2018 ◽  
Vol 28 (11n12) ◽  
pp. 1719-1737
Author(s):  
Hao Wang ◽  
Xiaofang Zhang ◽  
Bin Liang ◽  
Qian Zhou ◽  
Baowen Xu
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Network Models ◽  
Neural Model ◽  
Attention Mechanism ◽  
Support Vector ◽  
Neural Network Models ◽  
Long Distance ◽  
Sentence Level

In the field of target-based sentiment analysis, the deep neural model combining attention mechanism is a remarkable success. In current research, it is commonly seen that attention mechanism is combined with Long Short-Term Memory (LSTM) networks. However, such neural network-based architectures generally rely on complex computation and only focus on single target. In this paper, we propose a gated hierarchical LSTM (GH-LSTMs) model which combines regional LSTM and sentence-level LSTM via a gated operation for the task of target-based sentiment analysis. This approach can distinguish different polarities of sentiment of different targets in the same sentence through a regional LSTM. Furthermore, it is able to concentrate on the long-distance dependency of target in the whole sentence via a sentence-level LSTM. The final results of our experiments on multi-domain datasets of two languages from SemEval 2016 indicate that our approach yields better performance than Support Vector Machine (SVM) and several typical neural network models. A case study of some typical examples also makes a supplement to this conclusion.

scholarly journals Tourism Review Sentiment Classification Using a Bidirectional Recurrent Neural Network with an Attention Mechanism and Topic-Enriched Word Vectors

2018 ◽  
Vol 10 (9) ◽  
pp. 3313 ◽  
Author(s):  
Qin Li ◽  
Shaobo Li ◽  
Jie Hu ◽  
Sen Zhang ◽  
Jianjun Hu
Keyword(s):  
Neural Network ◽  
Data Analysis ◽  
Sentiment Analysis ◽  
Recurrent Neural Network ◽  
Topic Model ◽  
Online Reviews ◽  
Attention Mechanism ◽  
Sentiment Classification ◽  
Vector Representation ◽  
Gated Recurrent Unit

Sentiment analysis of online tourist reviews is playing an increasingly important role in tourism. Accurately capturing the attitudes of tourists regarding different aspects of the scenic sites or the overall polarity of their online reviews is key to tourism analysis and application. However, the performances of current document sentiment analysis methods are not satisfactory as they either neglect the topics of the document or do not consider that not all words contribute equally to the meaning of the text. In this work, we propose a bidirectional gated recurrent unit neural network model (BiGRULA) for sentiment analysis by combining a topic model (lda2vec) and an attention mechanism. Lda2vec is used to discover all the main topics of review corpus, which are then used to enrich the word vector representation of words with context. The attention mechanism is used to learn to attribute different weights of the words to the overall meaning of the text. Experiments over 20 NewsGroup and IMDB datasets demonstrate the effectiveness of our model. Furthermore, we applied our model to hotel review data analysis, which allows us to get more coherent topics from these reviews and achieve good performance in sentiment classification.

scholarly journals A data-driven neural network architecture for sentiment analysis

2019 ◽  
Vol 53 (1) ◽  
pp. 2-19 ◽  
Author(s):  
Erion Çano ◽  
Maurizio Morisio
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Network Architecture ◽  
Network Models ◽  
Data Sets ◽  
Feature Maps ◽  
Neural Network Architecture ◽  
Neural Network Models ◽  
Content Type ◽  
Max Pooling

Purpose The fabulous results of convolution neural networks in image-related tasks attracted attention of text mining, sentiment analysis and other text analysis researchers. It is, however, difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. The purpose of this paper is to present the creation steps of two big data sets of song emotions. The authors also explore usage of convolution and max-pooling neural layers on song lyrics, product and movie review text data sets. Three variants of a simple and flexible neural network architecture are also compared. Design/methodology/approach The intention was to spot any important patterns that can serve as guidelines for parameter optimization of similar models. The authors also wanted to identify architecture design choices which lead to high performing sentiment analysis models. To this end, the authors conducted a series of experiments with neural architectures of various configurations. Findings The results indicate that parallel convolutions of filter lengths up to 3 are usually enough for capturing relevant text features. Also, max-pooling region size should be adapted to the length of text documents for producing the best feature maps. Originality/value Top results the authors got are obtained with feature maps of lengths 6–18. An improvement on future neural network models for sentiment analysis could be generating sentiment polarity prediction of documents using aggregation of predictions on smaller excerpt of the entire text.

scholarly journals Constructive Learning of Deep Neural Networks for Bigdata Analysis

2020 ◽  
Vol 9 (12) ◽  
pp. 311-322
Author(s):  
Soha Abd Mohamed El-Moamen ◽  
Marghany Hassan Mohamed ◽  
Mohammed F. Farghally
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Binary Classification ◽  
Network Models ◽  
Classification Model ◽  
Neural Network Models ◽  
Constructive Learning ◽  
The Neural Network ◽  
Rapid Pace ◽  
Better Than

The need for tracking and evaluation of patients in real-time has contributed to an increase in knowing people’s actions to enhance care facilities. Deep learning is good at both a rapid pace in collecting frameworks of big data healthcare and good predictions for detection the lung cancer early. In this paper, we proposed a constructive deep neural network with Apache Spark to classify images and levels of lung cancer. We developed a binary classification model using threshold technique classifying nodules to benign or malignant. At the proposed framework, the neural network models training, defined using the Keras API, is performed using BigDL in a distributed Spark clusters. The proposed algorithm has metrics AUC-0.9810, a misclassifying rate from which it has been shown that our suggested classifiers perform better than other classifiers.

Negative emotion diffusion and intervention countermeasures of social networks based on deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 4935-4945
Author(s):  
Qiuyun Cheng ◽  
Yun Ke ◽  
Ahmed Abdelmouty
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Negative Emotion ◽  
Sentiment Classification ◽  
Classification Model ◽  
Learning Models ◽  
Data Set ◽  
Position Information ◽  
Processing Technologies ◽  
And Training

Aiming at the limitation of using only word features in traditional deep learning sentiment classification, this paper combines topic features with deep learning models to build a topic-fused deep learning sentiment classification model. The model can fuse topic features to obtain high-quality high-level text features. Experiments show that in binary sentiment classification, the highest classification accuracy of the model can reach more than 90%, which is higher than that of commonly used deep learning models. This paper focuses on the combination of deep neural networks and emerging text processing technologies, and improves and perfects them from two aspects of model architecture and training methods, and designs an efficient deep network sentiment analysis model. A CNN (Convolutional Neural Network) model based on polymorphism is proposed. The model constructs the CNN input matrix by combining the word vector information of the text, the emotion information of the words, and the position information of the words, and adjusts the importance of different feature information in the training process by means of weight control. The multi-objective sample data set is used to verify the effectiveness of the proposed model in the sentiment analysis task of related objects from the classification effect and training performance.

Double Multi-Head Attention-Based Capsule Network for Relation Classification

2021 ◽  
Author(s):  
Hongjun Heng ◽  
Renjie Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Language Processing ◽  
Layer Structure ◽  
Single Layer ◽  
Network Models ◽  
Classification Model ◽  
Neural Network Models ◽  
Comparable Performance ◽  
Relation Classification

Semantic relation classification is an important task in the field of nature language processing. The existing neural network relation classification models introduce attention mechanism to increase the importance of significant features, but part of these attention models only have one head which is not enough to capture more distinctive fine-grained features. Models based on RNN (Recurrent Neural Network) usually use single-layer structure and have limited feature extraction capability. Current RNN-based capsule networks have problem of improper handling of noise which increase complexity of network. Therefore, we propose a capsule network relation classification model based on double multi-head attention. In this model, we introduce an auxiliary BiGRU (Bidirectional Gated Recurrent Unit) to make up for the lack of feature extraction performance of single BiGRU, improve the bilinear attention through double multihead mechanism to enable the model to obtain more information of sentence from different representation subspace and instantiate capsules with sentence-level features to alleviate noise impact. Experiments on the SemEval-2010 Task 8 benchmark dataset show that our model outperforms most of previous state-of-the-art neural network models and achieves the comparable performance with F1 score of 85.3% in capsule network.

Prediction of Characteristics of Wave Breaking in Shallow Water Using Neural Network Techniques

2017 ◽  
Author(s):  
Nicholas Kouvaras ◽  
Manhar R. Dhanak
Keyword(s):  
Neural Network ◽  
Wave Height ◽  
Predictive Models ◽  
Wave Breaking ◽  
Laboratory Experiments ◽  
Network Models ◽  
Classification Model ◽  
Neural Network Models ◽  
Wave Setup ◽  
Fringing Reef

The characteristics of wave breaking over a fringing reef are considered using a set of laboratory experiments and the results are used to develop associated predictive models. Various methods are typically used to estimate the characteristics of nearshore wave breaking, mostly based on empirical, analytical and numerical techniques. Deo et al. (2003) used an artificial neural network approach to predict the breaking wave height and breaking depth for waves transforming over a range of simply sloped bottoms. The approach is based on using available representative data to train appropriate neural network models. The Deo et al. (2003) approach is extended here to predict other characteristics of wave breaking, including the type of wave breaking, and the position of breaking over a fringing reef, as well as the associated wave setup, and the rate of dissipation of wave energy, based on observations from a series of laboratory experiments involving monochromatic waves impacting on an idealized reef. Yao et al. (2013) showed that for such geometry, the critical parameter is the ratio of deep-water wave height to the depth of the shallow reef flat downstream of the position of wave breaking, H1/hs, rather than the slope of the reef. H1/hs, and the wave frequency parameter, fH1/g, are provided as inputs to the neural network models of the feed-forward type that are developed to predict the above characteristics of wave breaking. The models are trained using the experimental data. The breaker type classification model has a success rate of over 95%, implying that the neural networks method outperforms previously used criteria for classifying breaker types. The numeric prediction model for the dimensionless position of wave breaking also performs well, with a high degree of correlation between the predicted and actual positions of wave breaking. The performance is higher when only the plunging breaker instances are considered, but lower when only the spilling breaker instances are considered. The corresponding neural network models for wave setup within the surf zone and the difference in energy flux between the incident and broken wave have success rates of approximately 89% and 94% respectively. The method may be extended to provide predictive models for consideration of a range of natural coastal conditions, random waves, and various bottom profiles and complex geometry, based on training and testing of the models using representative field and laboratory observational data, in support of accurate prediction of near-shore wave phenomena.

Sign in / Sign up

Export Citation Format

Share Document