Accepting or Rejecting Students’ Self-grading in their
Final Marks by using Data Mining
First A. Author1, Second B. Author2, and Third C. Author3[Font: Times New Roman, Size:11]
1Member, Institute/Organization name[Font: Times New Roman, Size:11]
2Member, Institute/Organization name[Font: Times New Roman, Size:11]
3Member, Institute/Organization name[Font: Times New Roman, Size:11]
Abstract—In this paper we propose a methodology based on data mining andself-evaluation in order to predict whether an instructor will or will not accept the students’ proposed marks in a course. This is an on-going work in which we have evaluated the usage of classification techniques and cost-sensitive corrections. We have carried out several experiments
…show more content…
II. METHODOLOGY
The methodology that we have used in this study is as follows.During the course, students are evaluated by means of a multiple choice testing that is an effective assessment technique. Before the final exam date, all students are requested to self-grade. Students propose the mark/grade that they think they should get for the course. Then, the instructor accepts or declines the proposed mark of each student as the final mark for the course. This way, only students whose score was declined by the instructor will have to sit the final exam. Finally, we try to predict the instructor’s decision of accepting or declining the score proposed by students.
We have used two different (initial and new) data mining approaches (see Figure 1).
Figure 1. Approaches for predicting instructor’s decision.
The initial approach uses three numerical variables: the scoreobtained by students in the course’s activities, the proposed scores by students and the difference between these two previous scores.
Then, it applies traditional classification algorithms for predicting the instructor’s decision about whether to accept the proposed students’ scores (YES) or not (NO). The new approach uses the three previous variables as well as a self-evaluation questionnaire as another source of information. Then, it applies cost-sensitive classification [2] that is normally used for obtaining
Education is a long-term investment. We, as students, work hard to acquire knowledge and to hone our skills so that we may use them one day. The effort we put into a single assignment should be considered as both for that specific assignment and for our rounding as complete, educated individuals. And with this mindset, students should be motivated even more to put more effort and hard work into academics, with the goal of bettering themselves for the future and advancing their prospects as individuals. And with this hard work and effort will come progress, and this progress should be reflected in the grading—not necessarily on individual assignments, but on the student’s education as a
At the end of the course there should be some form of summative assessment; this enables the tutor to determine if the learning outcomes have been met by all or some of the learners.
From the very beginning of the course, teachers should begin to analyse their learners through initial assessment methods. The assessments best suited to guide improvements in student learning are quizzes, tests, writing assignments, and other assessments such as a group activity. These can easily give the teacher/tutor an insight into the learning needs of the learners. Also
There is a large variety of assessment methods available for assessing learners’ achievements. These include observation; questioning the learner; examining product evidence; discussion; witness testimony; looking at learner statements; recognising prior learning; simulated environment; skills tests; oral and written examinations; assignments; case studies and projects. Choosing the most appropriate assessment methods is vitally important, to help and support the learner and to ensure the job of the assessor is as straightforward, reliable and problem-free as possible.
Alfie Kohn discussed multiple fabulous points in his article, “Degrading to De-Grading”. The author suggests more effective ways to assess students’ progress other than numerical or letter grades. Kohn goes into detail about why our current grading system is flawed. Grades can cause students to lose interest in learning which causes them to stop taking challenges. If students are not engaged and interested than they are not retaining the information they are being taught. The grading system can also cause students to develop unhealthy competition with one another for instance, “I got a better grade than you!”. Indeed, grades are a wonderful concept, but they tend to be more hurtful than helpful. In some cases, grades can have positive effects on students. For example, setting goals for various assignments, or receiving help where they are struggling. Though, there are alternatives that could make positive changes in the system.
Assessment is carried out through formative (checks throughout the course), ipsative (to test against previous marks), and/ or summative (at end of course) activities to help the learner see their development whilst allowing the Assessor to give valuable feedback when appropriate. It’s purpose is to measure the learners understanding of the subject against the anticipated outcomes set by the criteria.
With all of the activities carried our by the learner (with or without the assessor) the assessor needs to make decisions on the learner's competence in relation to the requirements of the qualification. The assessor should make their judgements of success or not and provide constructive feedback to the learner in a way that best suits the individual. If any further action is necessary for the completion of the qualification criteria (i.e. more training, description of knowledge or other evidence of ability) then a further plan should be agreed to achieve this. All such information discussed and agreed should be recorded appropriately at each stage.
Initially in this assignment, I intend to describe and evaluate two different assessment methods, which I use to assess the progress of my learners.
When the student is presented with their final score the program should be able to give the student feedback according to their score
Internal validity of this study included data collection process and student personal interest in education. For example, students may have scored in exam because they concern about their own education. Reliability of this study instrument has not been tested. This is the first time this group will have this survey. There is no former survey to use as a standard to see if there are many changes.
The assessment method must take into account the characteristic of the learner and needs to be consistent and relevant to what is being assessed. The assessment will not only focus on improving the learning, it will measure their achievements and also remind the learner of how they are progressing.
In Rating Could Have Unintended Consequences Bastedo argues that “there are widespread examples of gaming and manipulation by colleges in the data they provide” thus hindering the credibility of any rating system. Furthermore, Bastedo proposes that the “pressure on institutions will be enormous” and will undoubtedly lead to some of these institutions to choose “unethical paths.” This is a natural response to a situation like this as any entity backed into a corner will utilize any means necessary for their survival. Reinforcing Bastedo’s argument is his claim that gathering the data would be a logistical nightmare in that the data available currently is of varying quality. To employ a rating system with current data would thus yield unreliable results. In essence, it does not appear Bastedo is definitively against the idea of a rating system but rather he is against diving in headfirst into employing a system when we have not yet learned of all its
Students will receive a final exam score of 1-5, derived from their performance on both the through-course assessment and the end-of-course
Abstract— Entrance examinations for post graduate courses in India like MCA,M.Tech etc happen mainly to select students for these courses.A study has been undertaken in order to see whether these entrance examinations test the aptitude of the students – if so to what extent and if not to what extent. In Karnataka these entrance tests are mainly conducted by the Karnataka Examination authority. This paper is part of a doctoral study which aims at building a decision support system to aid the question paper setting for such examinations. The authors have earlier studied several techniques to patternise the score of the students with the data and this paper is on application of Dempster-Shafer theory to this scenario. Dempster Shafer theory is mostly based on belief systems and these systems apply well in the given context, although they have their limitations.
Vasiljevic, Vukajlovic & Vasiljevic (2015) applied data mining techniques especially binary logistic regression method in the primary education domain. This study addressed the main research question; to what extent and on which memorials teachers, schools, students and their environment we can explain or predict school success and the level of student achievement. The authors proposed a system that performs data mining via