scholarly journals Sentiment Analysis Method based on Piecewise Convolutional Neural Network and Generative Adversarial Network

2019 ◽  
Vol 14 (1) ◽  
pp. 7-20 ◽  
Author(s):  
Changshun Du ◽  
Lei Huang
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Convolution Neural Network ◽  
Training Data ◽  
Sentence Structure ◽  
Analysis Model ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Text Sentiment Analysis

Text sentiment analysis is one of the most important tasks in the field of public opinion monitoring, service evaluation and satisfaction analysis under network environments. Compared with the traditional Natural Language Processing analysis tools, convolution neural networks can automatically learn useful features from sentences and improve the performance of the affective analysis model. However, the original convolution neural network model ignores sentence structure information which is very important for text sentiment analysis. In this paper, we add piece-wise pooling to the convolution neural network, which allows the model to obtain the sentence structure. And the main features of different sentences are extracted to analyze the emotional tendencies of the text. At the same time, the user’s feedback involves many different fields, and there is less labeled data. In order to alleviate the sparsity of the data, this paper also uses the generative adversarial network to make common feature extractions, so that the model can obtain the common features associated with emotions in different fields, and improves the model’s Generalization ability with less training data. Experiments on different datasets demonstrate the effectiveness of this method.

scholarly journals An Intelligent High Performance Automatic Sentiment Analysis Model Creation using Deep Convolution Neural Network

2020 ◽  
Vol 9 (3) ◽  
pp. 1288-1295
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Language Processing ◽  
High Performance ◽  
Convolution Neural Network ◽  
Support Vector ◽  
Analysis Model ◽  
Feature Sets ◽  
Deep Convolution Neural Network ◽  
Predictive Efficiency

With the advancement of data and communications technology, social media platforms and small news blogs serve as significant sources of data. In a small blogging forum, people can share their opinions, complaints, feelings and behaviors about the topic, current problems, and products. Emotional examination is an significant examination area in natural language processing that intends to target the emotion of the source material. Twitter is a well-liked stage where people around the globe can interrelate through user-produced messages. Data received from Twitter can give out as a primary source for many applications, together with event recognition, news recommendations as well as emergency supervision. In the categorization of emotions, recognition of suitable sub feature set acts an significant role. LIWC (Linguistic Inquiry and Word Count) is a research program for text examination to retrieve psychometric features from text documents. In this article this work present a psychometric method called the intelligent high performance automatic sentiment analysis model (IHPASAM) for Twitter emotion analysis. In this scheme, this work employed two main types of LIWC (linguistic processes along with psychological) as feature sets. To discover the predictive efficiency of dissimilar feature engineering systems, five supervised learning techniques (Naïve Bayes, logistic regression, k-nearest neighbor algorithm, support vector machines as well as convolution neural network) along with proposed Intelligent Deep Convolution Neural Network (IDCNN) are employed. Investigational outcome show that the ensemble feature sets provides a superior predictive efficiency than the individual set.

scholarly journals Generative Adversarial Network Performance in Low-Dimensional Settings

2021 ◽  
Vol 126 ◽  
Author(s):  
Felix Jimenez ◽  
Amanda Koepke ◽  
Mary Gregg ◽  
Michael Frey
Keyword(s):  
Neural Network ◽  
Network Performance ◽  
Training Data ◽  
High Dimensional ◽  
Generative Adversarial Network ◽  
Low Dimensions ◽  
Target Distribution ◽  
Adversarial Network ◽  
Low Dimensional ◽  
And Training

A generative adversarial network (GAN) is an artificial neural network with a distinctive training architecture, designed to createexamples that faithfully reproduce a target distribution. GANs have recently had particular success in applications involvinghigh-dimensional distributions in areas such as image processing. Little work has been reported for low dimensions, where properties of GANs may be better identified and understood. We studied GAN performance in simulated low-dimensional settings, allowing us totransparently assess effects of target distribution complexity and training data sample size on GAN performance in a simpleexperiment. This experiment revealed two important forms of GAN error, tail underfilling and bridge bias, where the latter is analogousto the tunneling observed in high-dimensional GANs.

Theme and sentiment analysis model of public opinion dissemination based on generative adversarial network

2019 ◽  
Vol 121 ◽  
pp. 160-167 ◽  
Author(s):  
E. Haihong ◽  
Hu Yingxi ◽  
Peng Haipeng ◽  
Zhao Wen ◽  
Xiao Siqi ◽  
...  
Keyword(s):  
Public Opinion ◽  
Sentiment Analysis ◽  
Analysis Model ◽  
Generative Adversarial Network ◽  
Adversarial Network

scholarly journals Label2label: Training a neural network to selectively restore cellular structures in fluorescence microscopy

2022 ◽  
Author(s):  
Lisa Sophie Kölln ◽  
Omar Salem ◽  
Jessica Valli ◽  
Carsten Gram Hansen ◽  
Gail McConnell
Keyword(s):  
Neural Network ◽  
Cellular Structure ◽  
Structural Similarity ◽  
Training Data ◽  
Cellular Structures ◽  
Target Structure ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Adversarial Network ◽  
Image Pairs

Immunofluorescence (IF) microscopy is routinely used to visualise the spatial distribution of proteins that dictates their cellular function. However, unspecific antibody binding often results in high cytosolic background signals, decreasing the image contrast of a target structure. Recently, convolutional neural networks (CNNs) were successfully employed for image restoration in IF microscopy, but current methods cannot correct for those background signals. We report a new method that trains a CNN to reduce unspecific signals in IF images; we name this method label2label (L2L). In L2L, a CNN is trained with image pairs of two non-identical labels that target the same cellular structure. We show that after L2L training a network predicts images with significantly increased contrast of a target structure, which is further improved after implementing a multi-scale structural similarity loss function. Here, our results suggest that sample differences in the training data decrease hallucination effects that are observed with other methods. We further assess the performance of a cycle generative adversarial network, and show that a CNN can be trained to separate structures in superposed IF images of two targets.

scholarly journals Cleaning our own dust: simulating and separating galactic dust foregrounds with neural networks

2020 ◽  
Vol 500 (3) ◽  
pp. 3889-3897 ◽  
Author(s):  
K Aylor ◽  
M Haq ◽  
L Knox ◽  
Y Hezaveh ◽  
L Perreault-Levasseur
Keyword(s):  
Neural Network ◽  
Interstellar Dust ◽  
Training Data ◽  
Microwave Background ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Learning Tasks ◽  
Polarized Emission ◽  
Non Gaussian ◽  
Planck Satellite

ABSTRACT Separating galactic foreground emission from maps of the cosmic microwave background (CMB) and quantifying the uncertainty in the CMB maps due to errors in foreground separation are important for avoiding biases in scientific conclusions. Our ability to quantify such uncertainty is limited by our lack of a model for the statistical distribution of the foreground emission. Here, we use a deep convolutional generative adversarial network (DCGAN) to create an effective non-Gaussian statistical model for intensity of emission by interstellar dust. For training data we use a set of dust maps inferred from observations by the Planck satellite. A DCGAN is uniquely suited for such unsupervised learning tasks as it can learn to model a complex non-Gaussian distribution directly from examples. We then use these simulations to train a second neural network to estimate the underlying CMB signal from dust-contaminated maps. We discuss other potential uses for the trained DCGAN, and the generalization to polarized emission from both dust and synchrotron.

scholarly journals Anomaly Detection Neural Network with Dual Auto-Encoders GAN and Its Industrial Inspection Applications

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3336 ◽  
Author(s):  
Ta-Wei Tang ◽  
Wei-Han Kuo ◽  
Jauh-Hsiang Lan ◽  
Chien-Fang Ding ◽  
Hakiem Hsu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Training Data ◽  
Labor Costs ◽  
Generative Adversarial Network ◽  
Detection Ability ◽  
Adversarial Network ◽  
Automated Optical Inspection ◽  
High Level

Recently, researchers have been studying methods to introduce deep learning into automated optical inspection (AOI) systems to reduce labor costs. However, the integration of deep learning in the industry may encounter major challenges such as sample imbalance (defective products that only account for a small proportion). Therefore, in this study, an anomaly detection neural network, dual auto-encoder generative adversarial network (DAGAN), was developed to solve the problem of sample imbalance. With skip-connection and dual auto-encoder architecture, the proposed method exhibited excellent image reconstruction ability and training stability. Three datasets, namely public industrial detection training set, MVTec AD, with mobile phone screen glass and wood defect detection datasets, were used to verify the inspection ability of DAGAN. In addition, training with a limited amount of data was proposed to verify its detection ability. The results demonstrated that the areas under the curve (AUCs) of DAGAN were better than previous generative adversarial network-based anomaly detection models in 13 out of 17 categories in these datasets, especially in categories with high variability or noise. The maximum AUC improvement was 0.250 (toothbrush). Moreover, the proposed method exhibited better detection ability than the U-Net auto-encoder, which indicates the function of discriminator in this application. Furthermore, the proposed method had a high level of AUCs when using only a small amount of training data. DAGAN can significantly reduce the time and cost of collecting and labeling data when it is applied to industrial detection.

scholarly journals Semi-Supervised Generative Adversarial Network for Sentiment Analysis of drug reviews

2021 ◽  
Author(s):  
Cristóbal Colón-Ruiz
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Automated Analysis ◽  
Learning Approaches ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Wide Range ◽  
Online User Reviews

<div>Sentiment analysis has become a very popular research topic and covers a wide range of domains such as economy, politics and health. In the pharmaceutical field, automated analysis of online user reviews provides information on the effectiveness and potential side effects of drugs, which could be used to improve pharmacovigilance systems. Deep learning approaches have revolutionized the field of Natural Language Processing (NLP), achieving state-of-the-art results in many tasks, such as sentiment analysis.</div><div>These methods require large annotated datasets to train their models. However, in most real-world scenarios, obtaining high-quality labeled datasets is an expensive and time-consuming task. In contrast, unlabeled texts task can be, generally, easily obtained. </div><div>In this work, we propose a semi-supervised approach based on a Semi-Supervised Generative Adversarial Network (SSGAN) to address the lack of labeled data for the sentiment analysis of drug reviews, and improve the results provided by supervised approaches in this task.</div><div>To evaluate the real contribution of this approach, we present a benchmark comparison between our semi-supervised approach and a supervised approach, which uses a similar architecture but without the generative adversal setting. </div><div>Experimental results show better performance of the semi-supervised approach when annotated reviews are less than ten percent of the training set, obtaining a significant improvement for the classification of neutral reviews, the class with least examples. To the best of our knowledge, this is the first study that applies a SSGAN to the sentiment classification of drug reviews. Our semi-supervised approach provides promising results for dealing with the shortage of annotated dataset, but there is still much room to improvement.</div>

Sign in / Sign up

Export Citation Format

Share Document