Assessing learners' understanding through node-link analysis /

Assessing learners' answer is a time consuming task that makes teachers or educators cut down the time they can devote to other important tasks. In fact, many academic examinations make heavy use of questions that require learners to write one or two sentences and which are worth for some amoun...

Full description

Saved in:
Bibliographic Details
Main Author: Adidah binti Lajis
Format: Thesis
Language:English
Published: Kuala Lumpur: Kulliyyah of Information and Communication Technology, International Islamic University Malaysia, 2011
Subjects:
Online Access:Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library.
Tags: Add Tag
No Tags, Be the first to tag this record!
LEADER 044080000a22003250004500
008 110608t2011 my ab g m 000 0 eng d
040 |a UIAM  |b eng 
041 |a eng 
043 |a a-my--- 
050 |a LB3060.37 
100 0 |a Adidah binti Lajis 
245 1 |a Assessing learners' understanding through node-link analysis /  |c by Adidah Binti Lajis 
260 |a Kuala Lumpur:   |b Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,   |c 2011 
300 |a xvii, 187 leaves :  |b ill. ;  |c 30cm. 
500 |a Abstract in English and Arabic. 
500 |a "A thesis submitted in fulfillment of the requirement for the degree of Doctor of Philosophy (Management Information System)."--On t.p. 
502 |a Thesis (Ph.D)--International Islamic University Malaysia, 2011. 
504 |a Includes bibliographical references (leaves 155-177). 
520 |a Assessing learners' answer is a time consuming task that makes teachers or educators cut down the time they can devote to other important tasks. In fact, many academic examinations make heavy use of questions that require learners to write one or two sentences and which are worth for some amount of marks. These short answer questions are highly valued and integral to the examinations but have been absent from computer-based assessment due to limitations in computerized marking technology. This thesis presents an assessment technique to assess learners' understanding for short free-text answer based on a hybrid approach with a combination of natural language processing, node-link representation and excess entropy. A textual answer of learner and expert are tagged according to its part of speech and only noun, verb, adverb, and adjective terms will be extracted. Each expert term is assigned to synonym terms before any comparison of a learner's term is performed. Later, the knowledge model for both expert and learners' are generated by converting the terms into a node link representation to uncover the hidden knowledge structure. By applying an information theory approach that is excess entropy, the generated knowledge models of an expert and learner are analyzed and results are in bits unit. Testing materials are obtained from 4 different domains that is computer science, medical, engineering, and science and also being categorized into 2 categories that are school and tertiary. Bloom taxonomy is used in categorizing the competency level test for each testing material. Pearson correlation, exact agreement and exactplus- adjacent agreement are used as an evaluation method. Results show computer science, and medical domain of tertiary level has achieved an excellent agreement of between 81% and 87%. And science domain of school level has achieved a fair to good agreement of between 48% and 66%. Experiment also shows that NL Scoring able to assess knowledge, understanding, and evaluation competency test for both tertiary and school level. Benchmarking NL Scoring with other baseline method such as vector space model, and latent semantic analysis has showed that NL Scoring performed better than them. Research hypotheses have indicated that proposed approaches is domain-independent, workable for sentence length of at least 3 words for both tertiary and school level, and has achieved a comparable result to other existing technique concerning short answer text assessment. 
596 |a 1 
650 |a Grading and marking (Students)  |x Data processing 
650 |a Educational tests and measurements  |x Data processing 
655 7 |a Theses, IIUM local 
690 |a Dissertations, Academic  |x Kulliyyah of Information and Communication Technology  |z IIUM 
710 2 |a International Islamic University Malaysia.  |b Kulliyyah of Information and Communication Technology 
856 4 |u https://lib.iium.edu.my/mom/services/mom/document/getFile/M5xSvQPIIZRCOx1Zlqst0j0xeXY6nuHq20121116160123843  |z Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. 
900 |a hab-zhmn 
999 |c 433223  |d 465987 
952 |0 0  |6 T LB003060.000037A000235A 002011  |7 0  |8 THESES  |9 753175  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o t LB3060.37A235A 2011  |p 00011220231  |r 2017-10-19  |t 2  |v 0.00  |y THESIS 
952 |0 0  |6 TS CDF LB003060.000037A000235A 002011  |7 0  |8 THESES  |9 846355  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o ts cdf LB3060.37A235A 2011  |p 11100326287  |r 2017-10-27  |t 1  |v 0.00  |y THESISDIG