RANCANGAN MODEL PENILAIAN UJIAN ESAI OTOMATIS MENGGUNAKAN METODE COSINE SIMILARITY DAN SYNONYM RECOGNITION

Putri Apricania, . (2023) RANCANGAN MODEL PENILAIAN UJIAN ESAI OTOMATIS MENGGUNAKAN METODE COSINE SIMILARITY DAN SYNONYM RECOGNITION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (182kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB I.pdf
Download (356kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (469kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (917kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB V.pdf
Download (215kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (218kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (145kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (542kB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (625kB)

Abstract

Essay assessment by the teacher takes a long time because they have to read student answers and match them with the answer key. To overcome this, an automatic scoring system using cosine similarity and synonym recognition methods was developed. The cosine similarity method measures the cosine similarity between students' answers and the correct answers using vectors, while synonym recognition identifies words with the same meaning as synonym keywords. This method is effective in providing accurate and consistent assessments and increasing the accuracy of the assessment. By using the term frequency, namely calculating the weight of words or the number of words that appear in a document. Based on the research results, it was found that the automatic essay examination scoring system using the cosine similarity and synonym recognition methods worked well. However, there is an error rate in predicting student scores with a Mean Absolute Error (MAE) of 8.4 for 20 test data and 11 for 10 test data which can be said to have a low system error rate. This research contributes to the development of an automatic essay exam scoring system that can speed up the assessment process and provide consistent assessments to students.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910511012] [Pembimbing: Jayanta] [Penguji 1: Didit Widiyanto] [Penguji 2: Bayu Hananto]
Uncontrolled Keywords: Essay exam, Synonym Recognition, Cosine Similarity, Term Frequency
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Putri Apricania
Date Deposited: 15 Aug 2023 04:20
Last Modified: 15 Aug 2023 04:20
URI: http://repository.upnvj.ac.id/id/eprint/25234

Actions (login required)

View Item View Item