Geschreven door studenten die geslaagd zijn Direct beschikbaar na je betaling Online lezen of als PDF Verkeerd document? Gratis ruilen 4,6 TrustPilot
logo-home
Tentamen (uitwerkingen)

Natural Language Processing for Mapping Exam Questions to the Cognitive Process Dimension

Beoordeling
-
Verkocht
-
Pagina's
13
Cijfer
A+
Geüpload op
24-08-2024
Geschreven in
2024/2025

2.1 Data acquisition This research is limited to the written exam questions used as research objects, namely the text of exam questions for various subjects held at the Faculty of Engineering and Science and the Faculty of Teaching and Education. This study needs text data about the end of the academic year exam. Samples were taken from the questions tested in the study program from both faculties of Universitas Muhammadiyah Purwokerto. 2.2 Research stage The method used in this study is simpler than the methods that have been used previously, namely applying the basic NLP concept to extract text to find the verb and then looking for the equivalent in the operational verb table (KKO - in Bahasa) [8] and [9]. Based on the framework presented, an outline of the general description of the steps taken in this research is illustrated in Figure 3. iJET ‒ Vol. 17, No. 13, 2022 7 Paper—Natural Language Processing for Mapping Exam Questions to the Cognitive Process Dimension Fig. 3. Research step The first stage of the model, as in Figure 3, is pre-processing the identification of the test question text under the framework of learning objectives in the RBT. At this stage, we do tokenization, case folding, stemming, and stop-word removal. The tokenization stage splits the input string based on each word that composes it, followed by case folding by reducing all letters to lower case, stemming, to transform the terms contained in a text into its root words, and stop-word removal, which removes non-descriptive words, for example, "yang (which),” “dan (and),” “di (at), “dari (from),” “ke (to),” and others. This stop-word removal aims to reduce index size and processing time. Furthermore, the feature extraction process is carried out using Part-of-speech (POS) tagging, which assigns POS markers or syntactic classes to each word in the corpus. The verbs resulting from the pre-processing are then matched with the list of operational verbs included in the KKO table. This KKO table contains a list of operational verbs used in RBT which is divided into six cognitive levels. 2.3 Testing design This NLP-based model was tested for its accuracy in generating information on the level of student cognition based on the RBT using eq. (1). This test compares the number of items that the model can map to the total items [30].

Meer zien Lees minder
Instelling
Natural Language Processing For Mapping
Vak
Natural Language Processing for Mapping

Voorbeeld van de inhoud

Paper—Natural Language Processing for Mapping Exam Questions to the Cognitive Process Dimension



Natural Language Processing for Mapping Exam
Questions to the Cognitive Process Dimension
https://doi.org/10.3991/ijet.v17i13.29095

Hindayati Mustafidah(), S. Suwarsito, Tito Pinandita
Universitas Muhammadiyah Purwokerto, Jawa Tengah, Indonesia




Abstract—Exam questions as a test instrument to measure educational
success must have good quality. This quality can be measured by the level of
cognition expected of students. The level of cognition reflects the mastery of
learning materials as a form of evaluation of the teaching and learning process
outlined in the curriculum. For this reason, the exam questions need to be mapped
into the cognitive process dimensions, namely based on the categories in the
Revised Bloom's Taxonomy (RBT). The mapping method used is Natural
Language Processing (NLP) as one of the fields of Artificial Intelligence
development. The stages in this mapping are pre-processing, including
tokenization, stemming, stop-word removal, and feature extraction using POS
Tagging. The output of this mapping process is in the form of categories of test
items into RBT: remembering (C1), understanding (C2), applying (C3),
analyzing (C4), evaluating (C5), and creating (C6). The classification results
obtained information that the exam questions prepared were still dominated at
the C2 cognitive level, which was indicated by the use of operational verbs in the
understanding category. The results of testing the method used produce an
accuracy of 82.22%. Thus, the NLP method can classify test items into Revised
Bloom's Taxonomy to determine the dimensions of students' cognitive processes.


Keywords—Natural Language Processing, exam questions, cognitive process
dimension, Revised Bloom's Taxonomy


1 Introduction

Education is a system, while learning is a form of educational activity. As a system,
education is a continuous activity. It involves many components, namely: a) raw input
(students), b) instrumental input (educators, objectives, materials/programs/curriculum,
methods, infrastructure, and facilities), c) environmental input (situation and conditions
of the educational environment, social, economic, cultural, security conditions), d) pro-
cess (implementation of education), and e) product (graduates) [1]. The availability of
educational components determines the quality of graduates both in quantity and qual-
ity and the functioning of each element according to its role in the implementation of
education as a system.




4 http://www.i-jet.org

, Paper—Natural Language Processing for Mapping Exam Questions to the Cognitive Process Dimension


An effective and efficient educational process will help assess the process and as-
sessment of learning outcomes; on the other hand, a good and correct, valid, and reliable
learning assessment will reveal the level of achievement and actual learning conditions.
The relationship between the elements of the educational process was proposed by [2]
which became the basis for other general models. The interpretation of Tyler's model,
in practice it is implemented into defining learning goals, organizing learning activities,
and evaluating the learning process implemented.
Educational objectives are formulated to describe student behavior reflected through
instructional objectives in the perspective of the course. The instructional goals are
elaborating educational plans [3]. The formulation of the proper educational purposes
will determine a good assessment. According to [4], a good assessment must describe
the expected learning outcomes. Assessment as a pedagogic ability [5] must be carried
out appropriately to get good feedback on the learning carried out. A good assessment
will obtain good feedback on the teaching carried out, which means that the quality of
education is also good.
The test is given to students as an assessment instrument in the form of items. Ref
[6] conveyed the stages of item development, namely: production, preparation, admin-
istration, reporting, documentation, and evaluation. Besides, ref [7] said that assessment
activities through written tests are traditional and common methods practiced in most
educational institutions today. Hence, questions must be given under the content of the
courses studied to meet learning objectives. Writing questions is a very challenging step
for questions makers. The situation is daring the teacher or items maker to compile
quality items that can be used to know the various cognitive levels. Thus, Bloom's Tax-
onomy or its revision named Revised Bloom's Taxonomy (RBT), has become general
references to guide for preparing test items for the teaching and learning process [8].
Interpretation of test results is conducted by making standard terms indicators of
what will be measured. These indicators must be derived from the formulated catego-
ries and subcategories, classifying educational objectives and the education taxonomy
classification. A goal formulation contains a verb which is a learning objective. This
verb describes the expected cognitive process, which includes six categories, namely
remembering (C1), understanding (C2), applying (C3), analyzing (C4), evaluating
(C5), and creating (C6) which previously consisted of knowledge, comprehension, ap-
plication, analysis, synthesis, and evaluation [9]. The six categories are known as Re-
vised Bloom Taxonomy, as shown in Figure 1.




Fig. 1. Bloom's Taxonomy and Revised Bloom's Taxonomy diagram [10]




iJET ‒ Vol. 17, No. 13, 2022 5

Geschreven voor

Instelling
Natural Language Processing for Mapping
Vak
Natural Language Processing for Mapping

Documentinformatie

Geüpload op
24 augustus 2024
Aantal pagina's
13
Geschreven in
2024/2025
Type
Tentamen (uitwerkingen)
Bevat
Vragen en antwoorden

Onderwerpen

$16.99
Krijg toegang tot het volledige document:

Verkeerd document? Gratis ruilen Binnen 14 dagen na aankoop en voor het downloaden kun je een ander document kiezen. Je kunt het bedrag gewoon opnieuw besteden.
Geschreven door studenten die geslaagd zijn
Direct beschikbaar na je betaling
Online lezen of als PDF

Maak kennis met de verkoper

Seller avatar
De reputatie van een verkoper is gebaseerd op het aantal documenten dat iemand tegen betaling verkocht heeft en de beoordelingen die voor die items ontvangen zijn. Er zijn drie niveau’s te onderscheiden: brons, zilver en goud. Hoe beter de reputatie, hoe meer de kwaliteit van zijn of haar werk te vertrouwen is.
StudyCenter1 Teachme2-tutor
Volgen Je moet ingelogd zijn om studenten of vakken te kunnen volgen
Verkocht
227
Lid sinds
2 jaar
Aantal volgers
91
Documenten
3850
Laatst verkocht
2 dagen geleden
Nursing school is hard! Im here to simply the information and make it easier!

My mission is to be your LIGHT in the dark. If you"re worried or having trouble in nursing school, I really want my notes to be your guide! I know they have helped countless others get through and thats all i want for YOU! Stay with me and you will find everything you need to study and pass any tests,quizzes abd exams!

4.3

28 beoordelingen

5
18
4
4
3
4
2
0
1
2

Recent door jou bekeken

Waarom studenten kiezen voor Stuvia

Gemaakt door medestudenten, geverifieerd door reviews

Kwaliteit die je kunt vertrouwen: geschreven door studenten die slaagden en beoordeeld door anderen die dit document gebruikten.

Niet tevreden? Kies een ander document

Geen zorgen! Je kunt voor hetzelfde geld direct een ander document kiezen dat beter past bij wat je zoekt.

Betaal zoals je wilt, start meteen met leren

Geen abonnement, geen verplichtingen. Betaal zoals je gewend bent via iDeal of creditcard en download je PDF-document meteen.

Student with book image

“Gekocht, gedownload en geslaagd. Zo makkelijk kan het dus zijn.”

Alisha Student

Bezig met je bronvermelding?

Maak nauwkeurige citaten in APA, MLA en Harvard met onze gratis bronnengenerator.

Bezig met je bronvermelding?

Veelgestelde vragen