Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Machine learning prediction for academic misconduct prediction: an analysis of binary classification metrics

Bulletin of Electrical Engineering and Informatics · Vol. 13 No. 1 (2023) · hlm. 388–395

DOI
10.11591/eei.v13i1.5629
ISSN
2089-3191, 2302-9285
Terbit
2023-12-13
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Academic misconduct is unethical behavior in academic work. To sustain integrity culture and mitigating unethical conducts among higher education institutions community, the academic misconduct detection must be done at an earlier stage. Thus, this study attempted to provide a new empirical contribution with the analysis of binary classification performances metrics to describe the ability of machine learning in predicting academic misconduct. Four machine learning algorithms have been used namely generalized linear model (GLM), logistic regression (LR), decision tree (DT), and random forest (RF). Beside performances comparison, this paper presents the analysis of academic misconduct factors that were constructed based on demography and fraud triangle theory (FTT). The findings showed that all the four machine learning algorithms have obtained good ability in the prediction models with the accuracy at above 80% and below 20% of the classification errors. Rationalization from the FTT attributes has shown as the most important factor in GLM, LR, and DT. In RF, opportunity of FTT attributes have become the most important. Compared to FTT attributes, demography attributes were not providing much benefits to all the machine learning models but remain applicable at very low weight correlations.

Kata kunci

Jaringan kolaborasi para penulis

35 penulis · 111 tautan kepenulisan bersama · 31 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universiti Teknologi MARA
  • Universiti Poly-Tech Malaysia
  • Universiti Utara Malaysia
  • Lampung University
  • Universiti Teknologi Petronas
  • Universitas Pembangunan Jaya
  • Sultan Abdul Halim Mu'adzam Shah International Islamic University
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Abdullah Sani Abd RahmanUniversiti Teknologi Petronas9
Norhayati BaharunUniversiti Teknologi MARA9
Nor Faezah Mohamad RaziUniversiti Teknologi MARA5
Nor Aslily SarkamUniversiti Teknologi MARA4
Masurah MohamadUniversiti Teknologi MARA4
Norliana OmarUniversiti Teknologi MARA3
Haslinawati Che HasanUniversiti Teknologi MARA3
Thuraiya MohdUniversiti Teknologi MARA2
Normah Binti OmarUniversiti Teknologi MARA2
Maheran ZakariaUniversiti Teknologi MARA2
Syed Redzwan Sayed RohaniUniversiti Teknologi MARA2
Anis Zulaikha Mohd ZukriUniversiti Teknologi MARA1
Siti Rasidah Md SakipUniversiti Teknologi MARA1
Syafiqah JamilUniversiti Teknologi MARA1
Shahirah Mohamed HatimUniversiti Teknologi MARA1
Nasiroh OmarUniversiti Teknologi MARA1
Teoh Sian HoonUniversiti Teknologi MARA1
Nadirah OthmanUniversiti Teknologi MARA1
Endang PitalokaAfiliasi tidak diketahui1
Yohanes Totok SuyotoUniversitas Pembangunan Jaya1
Noor Saatila Mohd IsaUniversiti Teknologi MARA1
Norhayati ZamriUniversiti Teknologi MARA1
Mohd Hadli Shah Mohamad YunusAfiliasi tidak diketahui1
Roshidi DinUniversiti Utara Malaysia1
Mohd Hilal MuhammadSultan Abdul Halim Mu'adzam Shah International Islamic University1
Hanizan Shaker HussainAfiliasi tidak diketahui1
Sunariya UtamaUniversiti Utara Malaysia1
Nor Hazlina MohammadUniversiti Teknologi MARA1
Anis Zafirah AzmiUniversiti Teknologi MARA1
Jufiza A. WahabUniversiti Teknologi MARA1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Machine learning prediction for academic misconduct prediction: an analysis of binary classification metrics</dc:title><dc:creator>Suraya Masrom</dc:creator><dc:creator>Nor Hafiza Abd Samad</dc:creator><dc:creator>Ratna Septiyanti</dc:creator><dc:creator>Nurshafinas Roslan</dc:creator><dc:creator>Rahayu Abdul Rahman</dc:creator><dc:subject>academic integrity</dc:subject><dc:subject>fraud triangle</dc:subject><dc:subject>classifier comparison</dc:subject><dc:subject>random forest</dc:subject><dc:subject>decision tree</dc:subject><dc:subject>logistic regression</dc:subject><dc:subject>generalized linear models</dc:subject><dc:subject>higher education ethics</dc:subject><dc:description xml:lang="en">Academic misconduct is unethical behavior in academic work. To sustain integrity culture and mitigating unethical conducts among higher education institutions community, the academic misconduct detection must be done at an earlier stage. Thus, this study attempted to provide a new empirical contribution with the analysis of binary classification performances metrics to describe the ability of machine learning in predicting academic misconduct. Four machine learning algorithms have been used namely generalized linear model (GLM), logistic regression (LR), decision tree (DT), and random forest (RF). Beside performances comparison, this paper presents the analysis of academic misconduct factors that were constructed based on demography and fraud triangle theory (FTT). The findings showed that all the four machine learning algorithms have obtained good ability in the prediction models with the accuracy at above 80% and below 20% of the classification errors. Rationalization from the FTT attributes has shown as the most important factor in GLM, LR, and DT. In RF, opportunity of FTT attributes have become the most important. Compared to FTT attributes, demography attributes were not providing much benefits to all the machine learning models but remain applicable at very low weight correlations.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2023-12-13</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v13i1.5629</dc:identifier><dc:identifier>10.11591/eei.v13i1.5629</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 13 No 1 (2023); 388-395</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/5629/3551</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>