Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476122Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Mohd. Juzaidin Ab Aziz, Prof. Dr. | |
| dc.contributor.author | Ali Muftah Benomran (P56125) | |
| dc.date.accessioned | 2023-10-06T09:13:48Z | - |
| dc.date.available | 2023-10-06T09:13:48Z | - |
| dc.date.issued | 2012-12-19 | |
| dc.identifier.other | ukmvital:73445 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476122 | - |
| dc.description | Automatic Essay Grading (AEG) system is defined as the computer technology that evaluates and grades of written prose. There are two types of essay answers: long essay answers, in this format the students will elaborately discuss a given topic. The next type is the short essay answer, where the essay is written in short sentences; there are two types of short essay answers, such as, the open ended short answer and the close ended short answer. This research has focused on the close ended short answers for computer subjects. Automatic essay grading for short answer is closely related to the task checking of text to text similarity. Automatically Marking short essay answers is one of the most complicated domains, because it heavily relies on the semantic similarity in meaning, to the degree to which any two sentences are similar in the meaning, where both have used similar words in meaning, in this case humans are able to easily judge, if the concepts are related to each other. Therefore it would be difficult for an automated grading system to grade an answer, when a student uses a synonym of a word in his/her answer instead of original word given in the answer scheme. The standard text similarity measures perform poorly on such tasks. Short answer only provides a limited content, because the length of the text is typically short, ranging from a single word to a dozen words. This research has proposed an Alternative Sentence Generator Method, which generates the alternative model answer based on the associated synonym dictionary. This research also proposes three algorithms combined such as, Commons Words (COW), Longest Common Subsequence (LCS) and Semantic Distance (SD), to be combined in the matching phase. These algorithms have been successfully used in many Natural Language Processing systems and have yielded efficient results. We have implemented and evaluated AEG system for short answers in English language based on these algorithms. The system was manually tested on 21 questions answered by three students and evaluated by teacher in class. The proposed system has resulted 82% correlation-style with human grading, which has made the system significantly better than the other state of the art systems. The main achievement of this study is the development of Automatic Essay Grading (AEG) for short answers in English language.,Master/Sarjana | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Automatic essay grading (AEG) system | |
| dc.subject | Close ended short answers | |
| dc.subject | English language | |
| dc.subject | Operating systems (Computers) | |
| dc.title | Automatic essay grading (AEG) system for close ended short answers in English language | |
| dc.type | theses | |
| dc.format.pages | 112 | |
| dc.identifier.callno | QA76.77.B444 2012 3 | |
| dc.identifier.barcode | 000464 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_73445+Source01+Source010.PDF Restricted Access | 1.63 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.