The Implementation of Winnowing Algorithm for Plagiarism Detection in Moodle-based E-learning

Hasan, Eric Ganiwijaya; Wicaksana, Arya; Hansun, Seng

doi:10.1109/icis.2018.8466429

Cited by 8 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By using ten combinations of k-gram values, windows, and prime numbers, the test results are shown in Table 6 and Figure 6. The combination of parameter values in this test was adopted from several previous studies [35]- [37], which resulted in a fairly high accuracy for similar cases. These values are used in this study Separately, the test was carried out again on ten essay questions with various combinations of parameters shown in Table 7.…”

Section: Testing the Combination Of K-gram Values Window And Prime Nu...mentioning

confidence: 99%

Automatic essay assessment in e-learning using winnowing algorithm

Amalia

Lestari

Wijayaningrum

et al. 2022

IJEECS

View full text Add to dashboard Cite

<span>The pandemic has caused almost all educational institutions to use online learning media to support learning activities. E-learning is a technology that is widely used because it can accommodate all learning activities. However, in general, e-learning can only perform automatic assessments for multiple choice answers but not for essay answers, so that manual assessment by the teacher becomes difficult and takes a long time. In this study, the winnowing algorithm was applied to the automatic assessment process on students' essay answers by measuring their similarity to the teacher's answer key. The stages in the automatic assessment using the winnowing algorithm begin with forming a series of k-grams, calculating the hash value, forming a window from the hash value, calculating the fingerprint value, and calculating the Jaccard Coefficient to obtain the percentage of text similarity results. The test results show that the winnowing algorithm can provide good performance when the answers to questions are in the form of short entries with the number of hashes not smaller than the window value. Meanwhile, on questions with long answers, the winnowing algorithm can still work well with an average difference of 5.2% from the results of the assessment carried out by the teacher.</span>

show abstract

Section: Testing the Combination Of K-gram Values Window And Prime Nu...mentioning

confidence: 99%

Automatic essay assessment in e-learning using winnowing algorithm

Amalia

Lestari

Wijayaningrum

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…Panjang k disini berupa parameter yang di input atau ditentukan oleh user [3]. Selanjutnya adalah tahapan perhitungan nilai hash, tahap ini yaitu menghitung nilai hash dari pembentukan rangkaian k-gram untuk mengubah karakter menjadi sebuah kode atau nilai yang kemudian akan menjadi penanda dalam mendapat informasi [4]. Tahap selanjutnya adalah pembentukan window, tahap ini nilai hash yang telah diperoleh akan dibagi ke dalam window yang berukuran w. Dimana w adalah nilai parameter yang di input atau ditentukan oleh user [5].…”

Section: Pendahuluanunclassified

“…Tahap selanjutnya adalah pembentukan window, tahap ini nilai hash yang telah diperoleh akan dibagi ke dalam window yang berukuran w. Dimana w adalah nilai parameter yang di input atau ditentukan oleh user [5]. Selanjutnya adalah tahapan pemilihan nilai fingerprint, pada tahapan ini akan dipilih nilai hash terkecil dari setiap window untuk dijadikan nilai fingerprint, jika terdapat nilai hash yang sama maka akan diambil nilai hash yang paling kanan untuk dijadikan nilai fingerprint [4]. Tahap terakhir adalah persamaan jaccard coefficient, yaitu Nilai fingerprint yang diperoleh akan digunakan dalam persamaan jaccard coefficient untuk mengukur persentase kesamaan teks.…”

Section: Pendahuluanunclassified

“…Dalam penelitian ini penulis memaparkan beberapa penelitian terdahulu yang digunakan sebagai ajuan dari penelitian ini yaitu memberikan rekomendasi untuk menggunakan algoritma winnowing ataupun algoritma lain yang memiliki metode sama dalam mendeteksi plagiat diantaranya yaitu : automatic essay grading system for japanese language examination using winnowing algorithm [5], detecting documents plagiarism using winnowing algorithm and k-gram method [6], rabin-karp and winnowing algorithm fot statistics of text document plagiarism detection [7], deteksi kemiripan dokumen bahasa indonesia menggunakan algoritma smithwaterman dan algoritma nazief & andriani [8], the implementation of winnowing algorithm for plagiarism detection in moodle-based elearning [4], analisis perbandingan algoritma rabin-karp dan levenshtein distance dalam menghitung kemiripan teks [9], aplikasi pendeteksi dugaan awal plagiarisme pada tugas siswa dan mahasiswa berdasarkan kemiripan isi teks menggunakan algoritma levenshtein distance [10].…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Uji Plagiarism pada Tugas Mahasiswa Menggunakan Algoritma Winnowing

Ramli

Cokrowibowo

Rustan

2021

JACOST

View full text Add to dashboard Cite

Plagiarism is the act of taking or plagiarizing the work, ideas or ideas of others either intentionally or unintentionally and claiming to be one's own work without mentioning the source or author. Often students plagiarize assignments given by the lecturer so that sometimes students just copy other people's assignments to complete the assignment. So that this can lead to dependence on other people in doing assignments and not being able to independently carry out assignments given by the lecturer. Currently, many plagiarism detection systems have been created to help reduce the level of plagiarism, one of which is the winnowing algorithm. In this study the authors used the winnowing algorithm to detect plagiarism in student assignments, namely programming source code, from the results of research conducted on 10 student assignments using the winnowing algorithm produced various similarity values as a percentage of similarity between two students tasks compared. With an average value of the overall similarity of the 10 tasks, namely 75.12%.

show abstract