TEXT ADVERTISEMENTS ANALYSIS USING CONVOLUTIONAL NEURAL NETWORKS

Journal URL

https://airccse.org/journal/ijdms/index.html

Volum URL

https://airccse.org/journal/ijdms/current2021.html


 TEXT ADVERTISEMENTS ANALYSIS USING CONVOLUTIONAL NEURAL NETWORKS


Authors

AbdulwahedAlmarimi and Asmaa Salem

ABSTRACT 

In this paper, we describe the developed model of the Convolutional Neural Networks CNN to a classification of advertisements. The developed method has been tested on both texts (Arabic and Slovak texts).The advertisements are chosen on a classified advertisements websites as short texts. We evolved a modified model of the CNN, we have implemented it and developed next modifications. We studied their influence on the performing activity of the proposed network. The result is a functional model of the network and its implementation in Java and Python. And analysis of model results using different parameters for the network and input data. The results on experiments data show that the developed model of CNN is useful in the domains of Arabic and Slovak short texts, mainly for some classification of advertisements

KEYWORDS 

Convolutional neural networks,

 advertisement text,

 back-propagation algorithm, 

classification, 

encoding of tex


CONCLUSION

In the paper we deal with one type of neural networks for a classification of advertisements. The model was tested on a short text of advertisements were written in Arabic and Slovak language. We have shown a way to get data from the advertisements websites. The modified model is qualified for using in the area for both languages independent on the obtained results. But it needs to analyze more texts. We designed the convolutional neural network model, it was applied in Java and Python programming languages and was examined using different activation functions, learning rate coefficients, filter count and its size. We have shown the results of the network using the proposed model



Comments

Post a Comment

Popular posts from this blog

Acceptance of E-procurement in Organisations: Using Structural Equation Modeling (SEM)

Image
 Acceptance of E-procurement in Organisations: Using Structural Equation Modeling (SEM) Muhammed S. Maddi1, Paul Davis2 and John Geraghty3, 1Dublin City University, Ireland & College of economic and Management Bani Walid City University, Libya and 2Dublin City University Business School, Ireland 3Dublin City University Mechanical and Manufacturing Engineering School, Ireland Abstract This research is concerned with the development of a realistic model for e-procurement adoption by organizations and groups observing the Rules of Islamic Sharia (RIS). This model is intended to be based on the behavioural control, subjective norms, and the recognition of the benefits and risks of eprocurement adoption. The developed model, “E-Procurement Adoption Model” (E-PAM), combined and extended two existing models previously used for information technology adoption. Central to the design of the E-PAM is the principle that a realistic model should consider all relevant psychological, social, ...
Read more

Hybrid Encryption Algorithms for Medical Data Storage Security in Cloud Database

Image
 Hybrid Encryption Algorithms for Medical Data Storage Security in Cloud Database Author Name Fenghua Zhang，Yaming Chen，Weiming Meng and Qingtao Wu, Henan University of Science and Technology, China Abstract Cloud database are derivatives of Cloud computing. At present, most medical institutions store data in cloud database. Although the cloud database improves the efficiency of use, it also poses a huge impact and challenge to the secure storage of data. The article proposes a hybrid algorithm to solve the data security problem in the hospital cloud database. First, the AES algorithm is improved. The improved algorithm is called P-AES algorithm. The P-AES algorithm is then combined with the RSA algorithm, called a hybrid algorithm. The experimental results show that the hybrid encryption algorithm has the advantages of fast encryption and decryption speed, high security, good processing ability for longer data, and can solve the data security problem in cloud database to a certain...
Read more
Image
INFLUENCE OF THE EVENT RATE ON DISCRIMINATION ABILITIES OF BANKRUPTCY PREDICTION MODELS Lili Zhang 1 , Jennifer Priestley 2 , and Xuelei Ni 3 1 Program in Analytics and Data Science, Kennesaw State University, Georgia, USA 2 Analytics and Data Science Institute, Kennesaw State University, Georgia, USA 3 Department of Statistics, Kennesaw State University, Georgia, USA ABSTRACT In bankruptcy prediction, the proportion of events is very low, which is often oversampled to eliminate this bias. In this paper, we study the influence of the event rate on discrimination abilities of bankruptcy prediction models. First the statistical association and significance of public records and firmographics indicators with the bankruptcy were explored. Then the event rate was oversampled from 0.12% to 10%, 20%, 30%, 40%, and 50%, respectively. Seven models were developed, including Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, ...
Read more