ارائه مدلی برای استخراج اطلاعات از مستندات متنی، مبتنی بر متن¬کاوی در حوزه یادگیری الکترونیکی
محورهای موضوعی : عمومىاحمدآقا کاردان 1 , مینا کیهانی نژاد 2 *
1 - Assistant Professor
2 - دانشگاه صنعتی امیرکبیر
کلید واژه: داده¬کاوی, متن¬کاوی, آموزش الکترونیکی, یادگیری الکترونیکی, سیستم مدیریت یادگیری ,
چکیده مقاله :
هنگامی که شبکه های کامپیوتری ستون اصلی علم و اقتصاد شد، حجم زیادی از مستندات در دسترس قرار گرفتند. به همین منظور، برای استخراج اطلاعات مفید از روش های متن کاوی استفاده می شود. متن کاوی یک حوزه پژوهشی مهم در کشف اطلاعات ناشناخته، فرضیات، و حقایق جدید به وسیله استخراج اطلاعات از اسناد مختلف است. همچنین متن کاوي آشکار کردن اطلاعات پنهان با استفاده از روشي است که در يک طرف توانايي مقابله با تعداد زيادي کلمات و ساختارهايي در زبان طبيعي را نشان مي‌دهد و از طرف ديگر اجازه مديريت ابهام و شک را می دهد. علاوه بر آن، متن کاوی به عنوان داده کاوی متن بیان می شود که معادل با تجزیه و تحلیل متون است و به فرایند استخراج اطلاعات از متن می پردازد و اطلاعات با کیفیت بالا را از میان الگوها و فرایندها استخراج می کند. همچنین به عنوان داده کاوی متن یا کشف دانش از پایگاه داده های متنی شناخته می شود و به فرایند استخراج الگوها یا دانش از اسناد متنی بیان می شود. روش تحقیق در این کار بدین صورت است که ابتدا به بررسي پژوهش‌های انجام شده در حوزه متن کاوی با تأکید بر روش ها و کاربردهای آن در آموزش الکترونیکی پرداخته شد. در طی این مطالعات، پژوهش های مرتبط در حوزه آموزش الکترونیکی طبقه بندی گردیدند. پس از طبقه بندی پژوهش‌ها، مسائل و راهکارهای مرتبط با مسائل مطرح شده در آن کارها، استخراج شدند. در همین راستا، در این مقاله ابتدا به تعریف متن کاوی پرداخته می‌شود. سپس فرایند متن کاوی و حوزه های کاربرد متن‌کاوی در آموزش الکترونیکی مورد بررسی قرار می‌گیرند. در ادامه روش‌های متن کاوی معرفی شده و تک تک این روش‌ها در حوزه آموزش الکترونیکی مطرح می‌گردد. در انتها ضمن استنتاج نکات مهم مطالعات انجام شده، مدلی جهت استخراج اطلاعات برای بهره‌برداری از روش‌های متن کاوی در یادگیری الکترونیکی پیشنهاد می شود.
۱٬۵۸۱ / ۵٬۰۰۰ When computer networks became the mainstay of science and economics, a large amount of documentation became available. For this purpose, text mining methods are used to extract useful information. Text mining is an important research field in discovering unknown information, hypotheses, and new facts by extracting information from various documents. Also, text mining is revealing hidden information using a method that shows the ability to deal with a large number of words and structures in natural language on the one hand, and allows the management of ambiguity and doubt on the other hand. In addition, text mining is defined as data mining of text, which is equivalent to text analysis and deals with the process of extracting information from text and extracting high quality information from patterns and processes. It is also known as text data mining or knowledge discovery from text databases and is defined as the process of extracting patterns or knowledge from text documents. The research method in this work is as follows: firstly, the research conducted in the field of text mining was investigated with an emphasis on its methods and applications in electronic education. During these studies, related researches were classified in the field of e-learning. After classifying the researches, issues and solutions related to the issues raised in those works were extracted. In this regard, in this article, the definition of text mining will be discussed first. Then the process of text mining and the fields of application of text mining in e-learning are examined. In the following, text mining methods are introduced and each of these methods is discussed in the field of electronic education. At the end, while deducing the important points of the conducted studies, a model for extracting information for the use of text mining methods in e-learning is proposed.
[1] Cristobal Romero, Sebastian Ventura, Enrique Garcia; “Data mining in course management systems: Moodle case study and tutorial”, Spain, Computers & Education 51 (2008) 368–384.
[2] Cristóbal Romero, Sebastián Ventura, Senior; “Educational Data Mining: A Review of the State-of-the-Art” Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEETransactions on Issue Date,,VOL: 40 Issue:6,On page(s): 601 – 618, 2010.
[3] Vishal Gupta, Gurpreet S. Lehal; “ A Survey of Text Mining Techniques and Applications” Journal of emerging technologies in web intelligence,VOL. 1, NO. 1, Aug.2009.
[4] Jong Hwan Suh, Chung Hoon Park, Si Hyun Jeon; “Applying text and data mining techniques to forecasting the trend of petitions filed to e-People” Information and Communication Technology Research and Development Center, Expert Systems with Applications 37, 7255–7268, 2010.
[5] Khaled Hammouda1 and Mohamed Kamel; "Data Mining in e-Learning", E-Learning Networked Environments and Architectures Advanced Information and Knowledge Processing, Springer, Part IV, 374-404,2007.
[6] Andreas Hotho, Andreas N¨urnberger, Gerhard Paaß; “A Brief Survey of Text Mining” machine learning, May 2005.
[7] Maomi Ueno; “Data mining and text mining technologies for collaborative learning in an ILMS “Samurai” Nagaoka University of Technology,on Advanced Learning Technologies, In IEEE international Conference on Advanced Learning Technologies, Washington, DC,1052-1053, 2004.
[8] Marta Zorrilla, Diego García,Elena Álvarez; “A Decision Support System to improve e-Learning Environments” Lausanne, Switzerland ,ACM, EDBT 2010, March 22-26, 2010.
[9] Youngjoong Ko, Jungyun Seo,” An effective sentence-extraction technique using contextual information and statistical approaches for text summarization”, Available online 4 March 2008, Pattern Recognition Letters 29 (2008) 1366–1371.
[10] Raymond J. Mooney,Razvan Bunescu,”Mining Knowledge from Text Using Information Extraction”, Department of Computer Sciences,University of Texas at Austin,1 University Station C0500, Austin, TX 787120233,2005.
[11] Shiqun Yin, Yuhui Qiu, Jike Ge; “ Research and Realization of Text Mining Algorithm on web”, International Conference on Computational Intelligence and Security Workshops, CISW,on ,413 - 416 ,15-19 Dec. 2007.
[12] Dirk Thorleuchter,Dirk Van den Poel,Anita Prinzie,”Mining ideas from textual information”, Expert Systems with Applications 37 (2010) 7182–7188.
[13] K. Rajaraman, Ah-Hwee Tan,"Topic Detection, Tracking and Trend Analysis Using Self-organizing Neural Networks", Kent Ridge Digital Labs,21 Heng Mui Keng Terrace, Singapore 119613,2001.
[14] P. van Mulbregt, I. Carp, L. Gillick, S. Lowe and J. Yamron, "Text Segmentation and Topic Tracking on Broadcast News via a Hidden Markov Model Approach", Dragon Systems, Inc,320 Nevada, Street Newton, MA 02460,1998.
[15] J.P. Yamron, I. Carp, L. Gillick, S. Lowe, and P. van Mulbregt,” Topic Tracking in a News Stream”, Dragon Systems, Inc. 320 Nevada Street, Newton, MA 02460,1999.
[16] Jon Fiscus, George Doddington, John Garofolo, Alvin Martin, "NIST’S 1998 Topic Detection and Tracking Evaluation (TDT2) ", National Institute of Standards and Technology, MD 20899-8940 USA,Aug 2007.
[17] Hubert Jin, Rich Schwartz, Sreenivasa Sista, Frederick Walls, "Topic Tracking for Radio, TV Broadcast, and Newswire", BBN Technologies70 Fawcett Street, Cambridge,MA, 02138.
Cambridge, MA 02138,Apr 1999.
[18] Minqing Hu,Bing Liu,” Mining and Summarizing Customer Reviews”, Department of Computer Science,University of Illinois at Chicago,851 South Morgan Street, Chicago, IL 60607-7053,2009.
[19] Yuen-Hsien Tseng, Chi-Jen Lin, Yu-I Lin,”Text mining techniques for patent analysis”, Available online 26 January 2007, Information Processing and Management 43 (2007) 1216–1247.
[20] Li Yu, Qiang Li,”A Novel Web Text Mining Method based on Semantic Polarity Analysis”,2009.
[21] Amelia Zafra, Cristóbal Romero, Sebastián Ventura,” Multiple instance learning for classifying students in learning management systems”, Department of Computer Science and Numerical Analysis, University of Cordoba, Spain, Expert Systems with Applications 38 (2011) 15020–15031.
[22] Ioannis Kazanidis, Stavros Valsamidis, Theodosios Theodosiou, Sotirios Kontogiannis," PROPOSED FRAMEWORK FOR DATA MINING IN E-LEARNING: THE CASE OF OPEN E-CLASS" IADIS International Conference Applied Computing 2009, Democritus University of Thrace, 2009.
[23] Jason J. Jung,” Social grid platform for collaborative online learning on blogosphere:A case study of eLearning BlogGrid”, Department of Computer Engineering, Yeungnam University, Dae-Dong, Gyeongsan, Republic of Korea, Expert Systems with Applications 36 (2009) 2177 2186.
[24] Bjornar Larsen and Chinatsu Aone,"Fast and Effective Text Mining Using Linear-time Document Clustering", SRA International, Inc. 4300 Fair Lakes Cow-l, Fairfax, VA 22033,1999.
[25] Fu-Ren Lin, Lu-Shih Hsieh, Fu-Tai Chuang,” Discovering genres of online discussion threads via text mining”, Computers & Education 52 (2009) 481–495.
[26] ursun Delen *, Martin D. Crossland,” Seeding the survey and analysis of research literature with text mining”, Department of Management Science and Information Systems, Expert Systems with Applications 34 (2008) 1707–1720.