Organizational Data Security with Persian Content Document Management Model for News Media

Document Type : Original Article

Authors

1 PhD student, Department of Information Technology Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran

2 Professor, Department of Information Technology Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran

Abstract

With the ever-increasing growth of Persian news texts in the digital world and the Internet, an important issue is the intelligent classification and management of news documents and our quick and cheap access to them. The results of the activities and actions carried out in this field are provided in the form of documents and documents and with spending a lot of time and money. These documents and documents contain valuable information and experiences that play an important role in the achievement of organizational goals and are considered one of the important management tools in the preparation of plans and decisions, considering that there are different algorithms and methods for text mining and also is being developed; But the main problem of these methods for organizations is maintaining the confidentiality of information. In addition to the use of modern science and technology, the principle of confidentiality of information should also be maintained. Many existing programs in the field of data mining and text mining work on the Internet, which actually violates the principle of confidentiality of information for organizations. Therefore, our main question refers to how to secure data using the intelligent document management model, which is one of the main concerns of every organization. On the other hand, collecting, storing, processing and analyzing this volume of information has become a serious challenge, and our goal is to use a system to manage the reception, preservation and maintenance of existing news, considering the aforementioned characteristics and the complexity of maintaining them. is. The complexity of organizations creates the need for centralization of news, documents, correct classification, correct circulation of news, ease of access to them. The management of news documents provides the possibility for organizations to correctly classify received or existing news and documents, preserve, maintain and retrieve them. In this research, which is of an applied type, experimental research methods and text mining tools have been used to carry it out. Also, in this research, the literature of document management, natural language processing and data analysis has been reviewed and explained, and then by studying the document management systems as a part of the knowledge management system, which is responsible for the acquisition, organization and sharing of knowledge in the organization. are introduced. By examining, analyzing and processing in this research, we come to the conclusion that the intelligent management model of Persian content documentation using the support vector machine model has an accuracy of 93.29, accuracy of 93.32, recall of 92.96 and error of 6.71.

Keywords

Main Subjects


Smiley face

 

[1]     B.Bina, M.Rahgozar, A.DehMobad, “Automatic Classification of Persian Texts”, 13th Annual Conference of the Iranian Computer Association, Kish Island, Computer Association, Sharif University of Technology, 2007.(In Persian)
[2]     I.Jamali, S.J.Mir-Abedini, A.Haroonabadi, “Presenting a model for Persian text classification using a combination of classification methods”, Journal of Telecommunications Engineering, Volume 7, Issue 23, 2017.(In Persian)
[3]     M.Karimimanesh, H.Shirazi, “Comparison of feature weighting methods in the document classification process”, First National Conference on New Approaches in Computer Engineering and Information Retrieval in Iran, 2013.(In Persian)
[4]     A.Siyahi, S.M.Hashemi, S.Mazraa, “Improving a Feature Selection Method for Text Classification with Text Mining Algorithms”, Second National Congress of Iranian New Technologies for Sustainable Development, Tehran, Center for Strategies for Sustainable Development, Mehr Arvand Institute of Higher Education, 2015. (In Persian)
[5]     P.NadKarni, M.Ohno-Machado, L.Chapman,  “ Natural language processing: an introduction”, Journal of the American Medical Informatics Association, 18(5), 544-551,  2011.
[6]     I.Moulinier, J.G.Ganascia, “Applying an existing machine learning algorithm to text categorization”, Paper presented at the International Joint Conference on Artificial Intelligence, 1995.
[7]     S.Eyheramendy, A.GenKin, W.Ju, H.Lewis, D.Madigan, “Sparse bayesian classifiers for text categorization”, Journal of Intelligence Community Research and Development, 13, 2003.
[8]     L.A.Francis, “Taming Text: An Introduction to Text Mining”, Paper presented at the Casualty Actuarial Society Forum, 2006.
[9]     I.A.BolshaKov, A.GelbuKh, “Computational linguistics: models, resources, applications: Instituto Politecnico Nacional”,  2004.
[10]  A.McCallum, K.Nigam, “A comparison of event models for naive bayes text classification”, Paper presented at the AAAI-98 worKshop on learning for text categorization, 1998.
[11]  Kardan.A, M.Keyhani Nejad, “Presenting a Model for Extracting Information from Text Documents Based on Text Mining in the Field of E-Learning”, Iranian Information and Communication Technology Scientific and Research Quarterly, Year 4, Issues 11 and 12, pp. 47-54,  2012.(In Persian)
[12]  M.Sheikhi, S.Akbarpour, A.Farzan, “Text Mining of Persian Texts for Its Classification”, Fourth Iranian Conference on Electrical and Electronic Engineering, 2012. (In Persian)
[13]  M.Bazghandi, Q.Tabrizi, J.Vafaei, “First International Conference on Natural Language and Handwriting Processing”, Semnan University, 2012.(In Persian)
[14]  P. MulaK, N. Talhar, “Analysis of distance measures using K-nearest neighbor algorithm on KDD dataset”, International Journal of Science and Research, 4(7), 2101-2104, 2015.
[15]  S.Arabi-Narei, M.Vahidi-Asl, B.Minaei-Bidgoli,  “Extracting Keywords for Persian Text Classification”, First Iranian Data Mining Conference, Tehran, https://civilica.com/doc/33094, 2007.(In Persian)
[16]  M.E.Basiri, S.Nemati, N.Ghasem Aghaei, “Comparison of Persian Text Classification Using K-Nearest Neighbor and fkNN Algorithms and Selecting Features Based on Information Gain and Document Frequency”, Thirteenth Annual Conference of the Iranian Computer Association, Kish Island, https://civilica.com/doc/41786, 2007.(In Persian)
[17]  A.Ghanbari-Sorkhi, F.Ebrahimi, “Improving the performance of Persian text classification using principal component analysis with the help of average recall and precision criteria”, 14th National Electrical Engineering Student nConference, Kermanshah, https://civilica.com/doc/121558, 2011.(In Persian)
[18]  M.Abedininia, L.Allahdadi, F.Sheikhi, “Exploring Persian texts on the web using semantic analysis and multi-layer information classification method”, First National Conference on New Approaches in Computer Engineering and Information Retrieval, Rasht, https://civilica.com/doc/225377, 2013.(In Persian)
[19]  P.Jalali, S.M.Hashemi, A.Siyahi, A.Heydari, “Presentation of a text classification method using filter feature reduction and machine learning techniques”, International Conference on New Research Findings in Electrical Engineering and Computer Science, Tehran, Nikan Institute of Higher Educationhttps, 2015.(In Persian)
[20]  H.PourAbbasi, M.Abbasi-Dezfuli, “Latin Text Classification with Filtering Covering and Naive Bayes Algorithms”, First National Conference on Computer and Information Technology, Sepidan, Islamic Azad University, Sepidan Branch, 2017.(In Persian)
[21]  M.Golparvar, S.J.Mousavi-Rad, “A Comparative Study of the Most Used Classification Algorithms in Customer Prediction and Validation”, Fifth National Conference on Applied Research in Management and Accounting, Tehran, Iranian Management Association.,  (2018). (In Persian)