استفاده از تکنیک های داده کاوی ترکیبی به سیستم خود ارزیابی مبتنی بر وب مطالعه و راهبردهای موجودی آموزش
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|20540||2009||10 صفحه PDF||سفارش دهید||5181 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 36, Issue 3, Part 1, April 2009, Pages 5523–5532
Traditional assessment tools, such as “Learning and Study Strategy Scale Inventory (LASSI)”, are typically pen-and-paper tests that require responses to a multitude of questions. This may easily lead to student’s resistance, fatigue and unwillingness to complete the assessment. To improve the situation, a hybrid data mining technique was applied to analyze the LASSI surveys of freshmen students at Tamkang University. The most significant contribution of this research is in dynamically reducing the number of questions while the LASSI assessment is proceeding. To verify the appliance of the proposed method, a web-based LASSI self-assessment system (Web-LSA) was developed. This system can be used as a guide to determine study disturbances for high-risk groups, and can provide counselors with fundamental information on which to base follow-up counseling services to its users.
Universities and colleges in Taiwan have recently acknowledged the importance of student affairs and have actively promoted counseling on career exploration, self-understanding, and interpersonal behavior for students. Hence, the student affairs office often plays a vital role in counseling students where they live and study. For example, the Consultation and Guidance Division of Student Affairs Office at Tamkang University could conceivably assist more than 27,000 students in the assessment of their learning and study strategies, personality characteristics, career interests, etc. and provide follow-up analyses and other services. Unfortunately, the number of available counselors in each school to provide these services is very limited. Conversely, the increased number of questions in a survey negatively influences the willingness of the participants to answer. Therefore, determining significant patterns in the scales and items in traditional assessments is essential to reducing the workload of counselors and improving the cooperation of its participants. As computers and network-related technologies rapidly and substantially improve, web-based testing (WBT) is becoming a common and effective type of assessment in different educational settings (He and Tymms, 2005, Sheader et al., 2006, Wang, 2007 and Wang et al., 2004). Although the web-based LASSI by Weinstein et al. is available at the web site developed by H&H Publishing Company (Weinstein & Palmer, 2002), its online completion is nonetheless time-consuming. 1.2. Objectives of the study The aims of this paper are: (1) To propose a hybrid data mining technique to examine the important characteristics of study strategy scales and their inter-relationships. By using fewer questions and thereby promoting better cooperation, learning problems will be predicated and information on study disturbances of high-risk groups will be readily provided. (2) To assist counselors and students to more efficiently use the LASSI assessment. A web-based Learning and Study Strategy self-assessment system (Web-LSA) was developed based on the rules discovered by the hybrid data mining approach. This system can be used as a pre-achievement measure for students participating in programs or courses focused on learning strategies and study skills through the Internet, and as a timesaving support tool for counselors. The remainder of this paper is organized into five sections; Section 2 describes the background knowledge of “Learning and Study Strategy Scale Inventory” (LASSI) and related data mining techniques. Section 3 introduces the proposed hybrid data mining approach. Section 4 is the comparative results of the experiment and the performance evaluation. Section 5 is the implementation of web-based
نتیجه گیری انگلیسی
The most significant contribution of this study is in effectively reducing the amount of questions into a meaningful pattern of questions and recommending a dynamic sequence of questions in LASSI scales according to the association rule tree. The proposed approach in this study is not to replace the original LASSI assessment but to provide an efficient model to support counselors in predicating and to prevent students’ unwillingness to being assessed. From the analysis of the survey of freshmen students at Tamkang University, hybrid data mining can reduce the amount of assessing items into 16 questions in the best case. Furthermore, only three to five minutes is required to complete an assessment through the Web-LSA. The base rule of Web-LSA can be revised by taking surveys of all students in the university as the raw data to improve the accuracy and practicability of our research. Moreover, our proposed hybrid data mining technique is also an efficient model for diagnostic and predictive web-based assessment, which can be applied to other questionnaires performed by Office of Student Affairs in establishing a gradual integrated online self-examination system.