Event Graph Neural Network for Opinion Target Classification of Microblog Comments

Author(s):  
Yan Xiang ◽  
Zhengtao Yu ◽  
Junjun Guo ◽  
Yuxin Huang ◽  
Yantuan Xian

Opinion target classification of microblog comments is one of the most important tasks for public opinion analysis about an event. Due to the high cost of manual labeling, opinion target classification is generally considered as a weak-supervised task. This article attempts to address the opinion target classification of microblog comments through an event graph convolution network (EventGCN) in a weak-supervised manner. Specifically, we take microblog contents and comments as document nodes, and construct an event graph with three typical relationships of event microblogs, including the co-occurrence relationship of event keywords extracted from microblogs, the reply relationship of comments, and the document similarity. Finally, under the supervision of a small number of labels, both word features and comment features can be represented well to complete the classification. The experimental results on two event microblog datasets show that EventGCN can significantly improve the classification performance compared with other baseline models.

2019 ◽  
Vol 14 (1) ◽  
pp. 124-134 ◽  
Author(s):  
Shuai Zhang ◽  
Yong Chen ◽  
Xiaoling Huang ◽  
Yishuai Cai

Online feedback is an effective way of communication between government departments and citizens. However, the daily high number of public feedbacks has increased the burden on government administrators. The deep learning method is good at automatically analyzing and extracting deep features of data, and then improving the accuracy of classification prediction. In this study, we aim to use the text classification model to achieve the automatic classification of public feedbacks to reduce the work pressure of administrator. In particular, a convolutional neural network model combined with word embedding and optimized by differential evolution algorithm is adopted. At the same time, we compared it with seven common text classification models, and the results show that the model we explored has good classification performance under different evaluation metrics, including accuracy, precision, recall, and F1-score.


2020 ◽  
Vol 17 (2) ◽  
pp. 445-458
Author(s):  
Yonghui Dai ◽  
Bo Xu ◽  
Siyu Yan ◽  
Jing Xu

Cardiovascular disease is one of the diseases threatening the human health, and its diagnosis has always been a research hotspot in the medical field. In particular, the diagnosis technology based on ECG (electrocardiogram) signal as an effective method for studying cardiovascular diseases has attracted many scholars? attention. In this paper, Convolutional Neural Network (CNN) is used to study the feature classification of three kinds of ECG signals, which including sinus rhythm (SR), Ventricular Tachycardia (VT) and Ventricular Fibrillation (VF). Specifically, different convolution layer structures and different time intervals are used for ECG signal classification, such as the division of 2-layer and 4-layer convolution layers, the setting of four time periods (1s, 2s, 3s, 10s), etc. by performing the above classification conditions, the best classification results are obtained. The contribution of this paper is mainly in two aspects. On the one hand, the convolution neural network is used to classify the arrhythmia data, and different classification effects are obtained by setting different convolution layers. On the other hand, according to the data characteristics of three kinds of ECG signals, different time periods are designed to optimize the classification performance. The research results provide a reference for the classification of ECG signals and contribute to the research of cardiovascular diseases.


2017 ◽  
Vol 1 (4) ◽  
pp. 271-277 ◽  
Author(s):  
Abdullah Caliskan ◽  
Mehmet Emin Yuksel

Abstract In this study, a deep neural network classifier is proposed for the classification of coronary artery disease medical data sets. The proposed classifier is tested on reference CAD data sets from the literature and also compared with popular representative classification methods regarding its classification performance. Experimental results show that the deep neural network classifier offers much better accuracy, sensitivity and specificity rates when compared with other methods. The proposed method presents itself as an easily accessible and cost-effective alternative to currently existing methods used for the diagnosis of CAD and it can be applied for easily checking whether a given subject under examination has at least one occluded coronary artery or not.


2021 ◽  
Vol 11 (19) ◽  
pp. 9226
Author(s):  
Burooj Ghani ◽  
Sarah Hallerberg

The automatic classification of bird sounds is an ongoing research topic, and several results have been reported for the classification of selected bird species. In this contribution, we use an artificial neural network fed with pre-computed sound features to study the robustness of bird sound classification. We investigate, in detail, if and how the classification results are dependent on the number of species and the selection of species in the subsets presented to the classifier. In more detail, a bag-of-birds approach is employed to randomly create balanced subsets of sounds from different species for repeated classification runs. The number of species present in each subset is varied between 10 and 300 by randomly drawing sounds of species from a dataset of 659 bird species taken from the Xeno-Canto database. We observed that the shallow artificial neural network trained on pre-computed sound features was able to classify the bird sounds. The quality of classifications were at least comparable to some previously reported results when the number of species allowed for a direct comparison. The classification performance is evaluated using several common measures, such as the precision, recall, accuracy, mean average precision, and area under the receiver operator characteristics curve. All of these measures indicate a decrease in classification success as the number of species present in the subsets is increased. We analyze this dependence in detail and compare the computed results to an analytic explanation assuming dependencies for an idealized perfect classifier. Moreover, we observe that the classification performance depended on the individual composition of the subset and varied across 20 randomly drawn subsets.


2021 ◽  
Vol 8 (3) ◽  
pp. 601
Author(s):  
Eko Prasetyo ◽  
Rani Purbaningtyas ◽  
Raden Dimas Adityo ◽  
Enrico Tegar Prabowo ◽  
Achmad Irfan Ferdiansyah

<p class="Abstrak">Ikan merupakan salah satu sumber protein hewani dan sangat diminati masyarakat Indonesia, dari survey bahan makanan yang diminati, bandeng peringkat keempat dibanding bahan makanan yang lain. Khususnya ikan bandeng, ikan ini menjadi satu dari enam ikan yang banyak dikonsumsi masyarakat selain tongkol, kembung, teri, mujair dan lele, maka ketelitian masyarakat ketika membeli ikan bandeng menjadi perhatian serius dalam memilih ikan bandeng segar. Deteksi kesegaran dengan menyentuh tubuh ikan dapat mengakibatkan kerusakan tanpa disengaja, maka deteksi kesegaran ikan harus dilakukan tanpa menyentuh ikan bandeng dengan memanfaatkan citra kondisi mata. Dalam riset ini, kami melakukan eksperimen implementasi klasifikasi kesegaran ikan bandeng sangat segar dan tidak segar berdasarkan mata menggunakan transfer learning dari empat CNN, yaitu Xception, MobileNet V1, Resnet50, dan VGG16. Dari hasil eksperimen klasifikasi dua kelas kesegaran ikan bandeng menggunakan 154 citra menunjukkan bahwa VGG16 mencapai kinerja terbaik dibanding arsitektur lainnya dimana akurasi klasifikasi mencapai 0.97. Dengan akurasi lebih tinggi dibanding arsitektur lainnya maka VGG16 relatif lebih tepat digunakan untuk klasifikasi dua kelas kesegaran ikan bandeng.</p><p class="Abstrak"> </p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>Fish, one source of animal protein, is an exciting food for Indonesia's people. From a survey of food-ingredients demanded, milkfish are ranked fourth compared to other food-ingredients. Especially for milkfish, this fish is one of the six fish consumed by Indonesia's people besides tuna, bloating, anchovies, tilapia, and catfish, so the exactitude of the people when buying is a severe concern in choosing fresh milkfish. Detection of freshness by touching the fish's body may cause unexpected destruction, so detecting the fish's freshness should be conducted without touching using the eye image. In this research, we conducted an experimental implementation of freshness milkfish classification (vastly fresh and not fresh) based on the eyes using transfer learning from several CNNs, such as Xception, MobileNet V1, Resnet50, and VGG16. The experimental results of the classification of two milkfish freshness classes using 154 images show that VGG16 achieves the best performance compared to other architectures, where the classification accuracy achieves 0.97. With higher accuracy than other architectures, VGG16 is relatively more appropriate for classifying two classes of milkfish freshness.</em></p>


1997 ◽  
Vol 08 (01) ◽  
pp. 55-61 ◽  
Author(s):  
Ahmad Ghazanfari ◽  
Anthony Kusalik ◽  
Joseph Irudayaraj

A multi-structure neural network (MSNN) classifier consisting of four discriminators followed by a maximum selector was designed and applied to classification of four grades of pistachio nuts. Each discriminator was a multi-layer feed-forward neural network with two hidden layers and a single-neuron output layer. Fourier descriptor of the nuts' boundaries and their area were used as the recognition features. The individual discriminators were trained using a biased technique and a back-propagation algorithm. The MSNN classifier gave an average classification performance of 95.0%. This was an increase of 14.8% over the performance of a multi-layer neural network (MLNN) with similar complexity for classifying the same set of patterns.


Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1537
Author(s):  
Xingxing Zhang ◽  
Shaobo Li ◽  
Jing Yang ◽  
Qiang Bai ◽  
Yang Wang ◽  
...  

In order to improve the accuracy of manipulator operation, it is necessary to install a tactile sensor on the manipulator to obtain tactile information and accurately classify a target. However, with the increase in the uncertainty and complexity of tactile sensing data characteristics, and the continuous development of tactile sensors, typical machine-learning algorithms often cannot solve the problem of target classification of pure tactile data. Here, we propose a new model by combining a convolutional neural network and a residual network, named ResNet10-v1. We optimized the convolutional kernel, hyperparameters, and loss function of the model, and further improved the accuracy of target classification through the K-means clustering method. We verified the feasibility and effectiveness of the proposed method through a large number of experiments. We expect to further improve the generalization ability of this method and provide an important reference for the research in the field of tactile perception classification.


In this chapter, the proposed optimization algorithm, kinetic gas molecule optimization (KGMO), that is based on swarm behaviour of gas molecules is applied to train a feedforward neural network for classification of ECG signals. Five types of ECG signals are used in this work including normal, supraventricular, brunch bundle block, anterior myocardial infarction (Anterior MI), and interior myocardial infarction (Interior MI). The classification performance of the proposed KGMO neural network (KGMONN) was evaluated on the Physiobank database and compared against conventional algorithms.


Sign in / Sign up

Export Citation Format

Share Document