Affix-based Distractor Generation for Tamil Multiple Choice Questions using Neural Word Embedding

2021 ◽  
Vol 13 (2) ◽  
Author(s):  
Shanthi Murugan ◽  
◽  
Balasundaram S R ◽  
Keyword(s):  
Large Scale ◽  
Research Effort ◽  
Multiple Choice ◽  
Automatic Generation ◽  
Difficulty Level ◽  
Multiple Choice Questions ◽  
Educational Domain ◽  
Part Of Speech ◽  
Educational Applications

Assessment plays an important role in learning and Multiple Choice Questions (MCQs) are quite popular in large-scale evaluations. Technology enabled learning necessitates a smart assessment. Therefore, automatic MCQ generation became increasingly popular in the last two decades. Despite a large amount of research effort, system generated MCQs are not useful in real educational applications. This is because of the inability to produce the diverse and human alike distractors. Distractors are the wrong choices given along with the correct answer (key) to confuse the examinee. Especially, in educational domain (grammar learning) the MCQs deal with affix-based or morphologically transformed distractors. In this paper, we present a method for automatic generation of affix-based distractors for fill-in-the-blanks for learning Tamil Vocabulary. Affix-based distractor generation relies on certain regularities manifest in high dimensional spaces. We investigate the quality of distractors generated by a number of criteria, including Part-Of-Speech, difficulty level, spelling, word co-occurrence, semantic similarity and affixation. We evaluated our proposed method in grammar based Multiple Choice Questions (MCQs) dataset. The result shows that affix-based distractors, yield significantly more plausible outcomes in certain grammar based questions.

scholarly journals EVALUASI PEMBELAJARAN UJIAN AKHIR SEMESTER MATA PELAJARAN BISNIS ONLINE KELAS XII SMK SUNAN DRAJAT LAMONGAN

2021 ◽  
Vol 5 (1) ◽  
pp. 1
Author(s):  
MIFTACHUL ULUM
Keyword(s):  
Quantitative Research ◽  
Multiple Choice ◽  
Difficulty Level ◽  
Multiple Choice Questions ◽  
Cronbach Alpha ◽  
Learning Evaluation ◽  
Online Business ◽  
Level Of Difficulty ◽  
Academic Year

At the end of each semester in an education unit, a learning evaluation is always carried out. One form of learning evaluation in schools is to carry out final semester exams. This study aims to determine the quality of online business lesson items for class XII SMK Sunan Drajat Lamongan in the odd semester 2017/2018 academic year in terms of validity, reliability, difficulty level and difference tests. This quantitative research is based on data from 21 student answer sheets from 25 multiple choice questions. The use of SPSS and Anates V4 software was used to measure the level of validity, reliability, difficulty level and item difference. The results showed that the validity value obtained was 15 items (60%) were declared invalid and 10 items (40%) were declared valid. Reliability of the items with a Cronbach Alpha value of 0.640> 0.6, which means that the instrument of the 25 items was declared reliable. The level of difficulty of the tested items obtained 5 items in the very easy category, 10 items in the easy category and 10 items in the moderate category. Of the 25 items, 8 items (32%) are good, 7 (28%) are sufficient and 10 (40%) are bad

scholarly journals Kualitas Soal Pilihan Ganda Kelas VI Tema 1 MI MHM Banjarsari Ngronggot Nganjuk

2021 ◽  
Vol 3 (2) ◽  
pp. 195-207
Author(s):  
Liana Mutholiin ◽  
Bustanul Arifin
Keyword(s):  
Multiple Choice ◽  
Difficulty Level ◽  
Validity And Reliability ◽  
Multiple Choice Questions ◽  
Final Assessment ◽  
Multiple Choice Items ◽  
Quantitative Descriptive ◽  
Academic Year ◽  
Assessment Questions

This research was conducted to find out how to compile and analyze the Odd End Semester Assessment questions at MI MHM Banjarsari, and to determine the quality of the multiple choice items of the Odd End Semester Assessment Grade VI Theme 1 MI MHM Banjarsari Academic Year 2019/2020. The research design used in the analysis of the quality of the multiple choice items Final Assessment of the odd semester class VI Theme 1 MI MHM Banjarsari Academic Year 2019/2020 is quantitative descriptive. Data collection in this study used document analysis method. The source of the data of this study was the question sheets and answer sheets of students participating in the Odd End Semester Assessment (PAS) of Class VI Theme 1 MI MHM Banjarsari. Calculation of the level of difficulty, different power, the effectiveness of deceit, the validity and reliability of the instrument in this study using the Anates V 0.4 program. The results of the research that have been done show that the quality of the final semester semester 1 question items in MI MHM Banjarsari in 2019/2020 from a total of 35 multiple choice questions viewed from the difficulty level obtained as many as 10 items (28.57%) with the difficulty level of questions in very easy category, 7 items (20%) in the easy category, 14 items (40%) in the medium category, 3 items (8.57%) in the difficult category, and 1 item (2.86%) in the very difficult category. Judging from the different power of the final semester assessment questions, theme 1 found 5 items (14.29%) in the very bad category, 13 items (37.14%) in the bad category, 6 items (17.14%) in the category enough, 10 items (28.57%) in the good category, and 1 item (2.86%) in the very good category. Judging from the deception of answers to the odd semester final assessment questions, there were 3 questions (8.57% in the very bad category, 6 questions (17.14%) in the bad category, 4 questions (11.48%) in the good category, and 22 questions (62.86%) in the very good category Judging from the validity of the odd semester final evaluation questions theme 1 obtained valid questions (significant / very significant) of 15 questions (42.86%) and for invalid questions a total of 20 questions (57.14%) In terms of reliability, it was obtained 0.81. Thus it can be concluded that the quality of the items can be said to be less good. [Penelitian ini dilakukan untuk mengetahui cara menyusun dan menganalisis soal Penilaian Akhir Semester ganjil di MI MHM Banjarsari, dan untuk mengetahui kualitas butir soal pilihan ganda Penilaan Akhir Semester ganjil kelas VI Tema 1 MI MHM Banjarsari Tahun Ajaran 2019/2020. Desain penelitian yang digunakan dalam analisis kualitas butir soal pilihan ganda Penilaan Akhir Semester ganjil kelas VI Tema 1 MI MHM Banjarsari Tahun Ajaran 2019/2020 adalah deskriptif kuantitatif. Pengumpulan data dalam penelitian ini menggunakan metodeanalisis dokumen. Sumber data penelitian ini adalah lembar soal dan lembarjawaban siswa peserta Penilaian Akhir Semester (PAS) ganjil Kelas VI Tema 1 MI MHM Banjarsari. Penghitungan tingkat kesulitan, daya beda, efektivitas pengecoh, validitas dan reliabilitas instrumen pada penelitian ini menggunakan program Anates V 0.4. Hasil penelitian yang telah dilakukan menunjukan bahwa kualitas butir soal penilaian akhir semester ganjil tema 1 di MI MHM Banjarsari tahun 2019/2020 dari total 35 soal pilihan ganda ditinjau dari tingkat kesukaran didapatkan sebanyak 10 butir soal (28,57%) dengan tingkat kesukaran soal dalam kategori sangat mudah, 7 butir soal (20%) dalam kategori mudah, 14 butir soal (40%) dalam kategori sedang, 3 butir soal (8,57%) dalam kategori sukar, dan 1 butir soal (2,86%) dalam kategori sangat sukar. Ditinjau dari daya beda soal penilaian akhir semester ganjil tema 1 didapatkan 5 butir soal (14,29%) dalam kategori sangat jelek, 13 butir soal (37,14%) dalam kategori jelek, 6 butir soal (17,14%) dalam kategori cukup, 10 butir soal (28,57%) dalam kategori baik, dan 1 butir soal (2,86%) dalam kategori sangat baik. Ditinjau dari pengecoh jawaban soal penilaian akhir semester ganjil tema 1 terdapat sebanyak 3 soal (8,57% dalam kategori sangat buruk, 6 soal (17,14%) dalam kategori buruk, 4 soal (11,48%) dalam kategori baik, dan 22 soal (62,86%) dalam kategori sangat baik. Ditinjau dari validitas soal penilaian akhir semester ganjil tema 1 didapatkan soal valid (signifikan/sangat signifikan) sejumlah 15 soal (42,86%) dan untuk soal yang tidak valid sejumlah 20 soal (57,14 %). Ditinjau dari reabilitas didapatkan sebesar 0.81. Dengan demikian dapat disimpulkan bahwa kualitas butir soal bisa dikatakan kurang baik]

CORRELATION OF DIFFICULTY INDEX AND DISCRIMINATING INDEX IN MEDICAL STUDENT’S ASSESSMENT.

2021 ◽  
pp. 9-10
Author(s):  
Bhoomika R. Chauhan ◽  
Jayesh Vaza ◽  
Girish R. Chauhan ◽  
Pradip R. Chauhan
Keyword(s):  
Medical Students ◽  
Formative Assessment ◽  
Item Difficulty ◽  
Multiple Choice ◽  
Multiple Choice Questions ◽  
Discriminating Power ◽  
Good Discriminator ◽  
Difficulty Index ◽  
The Relationship

Multiple choice questions are nowadays used in competitive examination and formative assessment to assess the student's eligibility and certification.Item analysis is the process of collecting,summarizing and using information from students' responses to assess the quality of test items.Goal of the study was to identify the relationship between the item difficulty index and item discriminating index in medical student's assessment. 400 final year medical students from various medical colleges responded 200 items constructed for the study.The responses were assessed and analysed for item difficulty index and item discriminating power. Item difficulty index an item discriminating power were analysed by statical methods to identify correlation.The discriminating power of the items with difficulty index in 40%-50% was the highest. Summary and Conclusion:Items with good difficulty index in range of 30%-70% are good discriminator.

scholarly journals Developing Computerized Adaptive Testing: An Experimental Research on Assessing the Mathematical Ability of 10 Graders (Vietnam K12 Education Program)

2019 ◽  
Author(s):  
Le Thai Hung ◽  
Nguyen Thi Quynh Giang ◽  
Tang Thi Thuy ◽  
Tran Lan Anh ◽  
Nguyen Tien Dung ◽  
...  
Keyword(s):  
Computerized Adaptive Testing ◽  
Multiple Choice ◽  
Adaptive Testing ◽  
Mathematical Ability ◽  
Difficulty Level ◽  
Multiple Choice Questions ◽  
Multiple Choice Tests ◽  
Mathematical Algorithms ◽  
Kolmogorov Smirnov ◽  
Initial Outcome

Computerized Adaptive Testing - CAT is a form of assessment test which requires fewer test questions to arrive at precise measurements of examinees' ability. One of the core technical components in building a CAT is mathematical algorithms which estimate examinee's ability and select the most appropriate test questions for those estimates. Those mathematical algorithms serve as a locomotive in operating the system of adaptive multiple-choice questions on computers.  Our research aims to develop essential mathematical algorithms to a computerised system of adaptive multiple-choice tests. We also build a question bank of 500 multiple-choice questions standardised by IRT theory with the difficulty level follows the normal distribution satisfying Kolmogorov-Smirnov test, to measure the mathematical ability of students in grade 10. The initial outcome of our experiment of the question bank shows: the question bank satisfies the requirements from a psychometric model and the constructed mathematical algorithms meets the criteria to apply in computerised adaptive testing.

Experience Versus Potential of Multiple-Choice Tests in Marketing Courses

1979 ◽  
Vol 1 (2) ◽  
pp. 24-33 ◽  
Author(s):  
James R. McMillan
Keyword(s):  
Multiple Choice ◽  
Multiple Choice Questions ◽  
High Quality ◽  
Test Form ◽  
Multiple Choice Tests ◽  
Choice Tests ◽  
Classroom Evaluation ◽  
Quality Objective ◽  
Multiple Choice Items

Most educators agree that classroom evaluation practices need improvement. One way to improve testing is to use high-quality objective multiple-choice exams. Almost any understanding or ability which can be tested by another test form can also be tested by means of multiple-choice items. Based on a survey of 173 respondents, it appears that marketing teachers are disenchanted with multiple-choice questions and use them sparingly. Further, their limited use is largely in the introductory marketing course even though there are emerging pressures for universities to take a closer look at the quality of classroom evaluation at all levels.

scholarly journals MSK30: a validated tool to assess clinical musculoskeletal knowledge

2019 ◽  
Vol 5 (1) ◽  
pp. e000495
Author(s):  
Danielle L Cummings ◽  
Matthew Smith ◽  
Brian Merrigan ◽  
Jeffrey Leggit
Keyword(s):  
Medical Students ◽  
Large Scale ◽  
Assessment Tool ◽  
Multiple Choice ◽  
School Curriculum ◽  
Average Score ◽  
Multiple Choice Questions ◽  
Modified Delphi ◽  
Multiple Choice Exam ◽  
Individual Education

BackgroundMusculoskeletal (MSK) complaints comprise a large proportion of outpatient visits. However, multiple studies show that medical school curriculum often fails to adequately prepare graduates to diagnose and manage common MSK problems. Current standardised exams inadequately assess trainees’ MSK knowledge and other MSK-specific exams such as Freedman and Bernstein’s (1998) exam have limitations in implementation. We propose a new 30-question multiple choice exam for graduating medical students and primary care residents. Results highlight individual deficiencies and identify areas for curriculum improvement.Methods/ResultsWe developed a bank of multiple choice questions based on 10 critical topics in MSK medicine. The questions were validated with subject-matter experts (SMEs) using a modified Delphi method to obtain consensus on the importance of each question. Based on the SME input, we compiled 30 questions in the assessment. Results of the large-scale pilot test (167 post-clerkship medical students) were an average score of 74 % (range 53% – 90 %, SD 7.8%). In addition, the tool contains detailed explanations and references were created for each question to allow an individual or group to review and enhance learning.SummaryThe proposed MSK30 exam evaluates clinically important topics and offers an assessment tool for clinical MSK knowledge of medical students and residents. It fills a gap in current curriculum and improves on previous MSK-specific assessments through better clinical relevance and consistent grading. Educators can use the results of the exam to guide curriculum development and individual education.

scholarly journals Comparison in the quality of distractors in three and four options type of multiple choice questions

2017 ◽  
Vol Volume 8 ◽  
pp. 287-291 ◽  
Author(s):  
AAG Rahma ◽  
Mahdi Shamad ◽  
Muawia E A Idris ◽  
Omer Elfaki ◽  
Walyeldin Elfakey ◽  
...  
Keyword(s):  
Multiple Choice ◽  
Multiple Choice Questions

Multiple Choice Questions of Information Entropy Analysis of Equivalent Options

2014 ◽  
Vol 556-562 ◽  
pp. 3726-3729
Author(s):  
Peng Dong Du ◽  
Tao Sun
Keyword(s):  
Information Entropy ◽  
Multiple Choice ◽  
Calculation Formula ◽  
Entropy Analysis ◽  
Multiple Choice Questions ◽  
Single Item ◽  
Problem Number

Single choice is one of the most extensive use of various types of test after test, the effectiveness of each option subject judgment can provide an important reference for the evaluation of the quality of test. In this paper, through the analysis of the single item choice information entropy problem, provides the calculation formula of this kind of problem number of equivalent options K.

Sign in / Sign up

Export Citation Format

Share Document