Sparse attention based separable dilated convolutional neural network for targeted sentiment analysis

Gan, Chenquan; Wang, Lu; Zhang, Zufan; Wang, Zhangyi

doi:10.1016/j.knosys.2019.06.035

Cited by 71 publications

(35 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is essential to study the specific control strategies (e.g., [29], [30]). In addition, it is worth trying to apply deep learning methods (e.g., [31], [32]) to explore the propagation behavior of malware in the cloud.…”

Section: Discussionmentioning

confidence: 99%

Dynamical Propagation Model of Malware for Cloud Computing Security

et al. 2020

Self Cite

View full text Add to dashboard Cite

Cloud-fog-edge computing especially cloud computing is providing a variety of services in many areas around the world and plays a vital role in cyber-physical-social systems (CPSS). Particularly, virtualization is one of main enabling technologies of cloud computing and realizes the dynamic deployment of computing tasks through the migration of virtual machines (VMs), so how to secure the virtual environment in the cloud is very crucial. The purpose of this paper is to address the issue of malware propagation among VMs under the infrastructure as a service (IaaS) architecture. Firstly, a dynamical propagation model is proposed to explore the important factors affecting the spread of malware, especially the impact of installing antivirus software in VMs. On this basis, a theoretical analysis for this model is investigated by means of differential dynamics, from which it is able to understand the dissemination behavior of malware under an infected cloud environment. Finally, some numerical simulations are conducted to verify the applicability and effectiveness of the proposed model. INDEX TERMS Cloud computing security, virtual environment, malware, propagation model, dynamical behavior.

show abstract

Section: Discussionmentioning

confidence: 99%

Dynamical Propagation Model of Malware for Cloud Computing Security

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For future work, we plan to investigate strategies for improving the performance of our system as follows: The first strategy is using multichannel embedding [ 48 ] on various DL models, such as RNN and CNN, where the pre-trained word embeddings are directly incorporated into the word embedding matrix. The advantages of multichannel embedding are that it can provide rich semantic/sentiment representations and avoid word embedding interference.…”

Section: Limitations and Future Directionsmentioning

confidence: 99%

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Mabrouk

Redondo

Kayed

2021

Sensors

View full text Add to dashboard Cite

Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers’ opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.

show abstract

“…With the rapid development of artificial intelligence, deep learning technology, which can automatically learn more complex features from complex data structures has been successfully applied in many fields, such as image processing [10], sentiment analysis [11, 12], channel estimation [13], signal classification [14], and modulation recognition [15]. Recently, the deep learning method has made significant progress in the field of MIMO channel quantisation and feedback, and has solved some problems in the CS technology.…”

Section: Introductionmentioning

confidence: 99%