Melola Discovery

← Melola Discovery

Akses terbuka Jurnal

Indonesian–Arabic Academic Translation Quality: A Comparative Content Analysis of ChatGPT and Google Translate

Ta'lim al-'Arabiyyah: Jurnal Pendidikan Bahasa Arab & Kebahasaaraban · Vol. 9 No. 2 (2025) · hlm. 207–223

DOI
10.15575/jta.v9i2.51510
ISSN
2721-5237, 2549-208X
Terbit
2025-12-25
Penerbit
UIN Sunan Gunung Djati Bandung
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

This study compares the quality of Indonesian–Arabic academic translations produced by Google Translate and ChatGPT (GPT-4), a topic rarely examined despite widespread MT use in Arabic Language Education programs. Using a qualitative descriptive design with content analysis, the data comprised ten purposively selected undergraduate thesis titles from Indonesian university repositories, including UIN Sunan Kalijaga, UIN Suska Riau, UIN Imam Bonjol Padang, and Universitas Muhammadiyah Makassar. Titles were selected for their academic rigor and need for conceptual precision and formal Arabic register. Translations were analyzed at the phrase level using a Hybrid MQM–Nababan–Baker rubric encompassing seven dimensions: accuracy, acceptability, readability, lexical equivalence, grammatical equivalence, cohesion and coherence, and academic fluency, each rated on a three-point scale. Validity was ensured through alignment with Arabic translation theory, equivalence frameworks, and MQM standards, while iterative consistency checks supported reliability. Results reveal clear differences. ChatGPT achieved an average score of 20.0 out of 21 points (93%), which is classified as Very Good and indicates strong suitability for academic publication. Google Translate scored 13.3 out of 21 points (63%), classified as Good, but requiring post-editing. ChatGPT excelled in contextual meaning, syntactic restructuring, accurate idhafah, case governance, consistent terminology, and scholarly style, whereas Google Translate showed literal transfer. This study enriches AI-assisted translation discourse by grounding evaluation in Arabic translation theory and pedagogy, emphasizing generative AI’s pedagogical potential as a complementary tool while reaffirming the indispensable role of human expertise in maintaining linguistic accuracy, rigor, and academic standards.

Kata kunci

Jaringan kolaborasi para penulis

31 penulis · 66 tautan kepenulisan bersama · 42 lintas organisasi

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

  • Muhammadiyah University of Yogyakarta
  • Universitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto
  • Walisongo State Islamic University
  • Muhammadiyah University of Surakarta
  • Islamic University of Riau
  • Universiti Brunei Darussalam
  • Politeknik Pariwisata NHI Bandung
  • Organisasi lain
  • 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
Mahyudin RitongaUniversitas Muhammadiyah Sumatera Barat2
RohmansyahAfiliasi tidak diketahui1
Budi Jaya PutraAfiliasi tidak diketahui1
Harun Joko PrayitnoMuhammadiyah University of Surakarta1
Sonny ZulhudaInternational Islamic University Malaysia1
Miftachul HudaSultan Idris Education University1
Mohamad AliMuhammadiyah University of Surakarta1
Adam MudinillahSekolah Tinggi Agama Islam Al-Hikmah1
Eva ArdinalInstitut Agama Islam Negeri Kerinci1
Tauhid TauhidSekolah Tinggi Agama Islam Negeri Mandailing Natal1
Naqiyah NaqiyahAfiliasi tidak diketahui1
Nita TrianaUniversitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto1
NaqiyahUniversitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto1
Laily LiddiniUniversitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto1
Hendro WidodoUniversitas Ahmad Dahlan1
Munirah MunirahMuhammadiyah University of Makassar1
Yayat HidayatMuhammadiyah University of Yogyakarta1
Vicky Adetia WulandariMuhammadiyah University of Yogyakarta1
Afdhal Fikri MirmaSunan Kalijaga State Islamic University Yogyakarta1
Zainal Abidin HajibUniversiti Sains Islam Malaysia1
Dyah Audia SyawwalinaMuhammadiyah University of Yogyakarta1
Ana Taqwa WatiMuhammadiyah University of Yogyakarta1
Lutfi HassanUniversiti Teknologi MARA1
Imelia Sahda SalsabillaWalisongo State Islamic University1
Nur AsiyahWalisongo State Islamic University1
Syaiful BakhriWalisongo State Islamic University1
Zarkasi ZarkasiAfiliasi tidak diketahui1

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: OAI-PMH (metadata jurnal) https://journal.uinsgd.ac.id/index.php/Talim/oai, pertama di-harvest 7 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Indonesian–Arabic Academic Translation Quality: A Comparative Content Analysis of ChatGPT and Google Translate</dc:title>
	<dc:creator>Alfitri, Alfitri</dc:creator>
	<dc:creator>Zakaria, Gamal Abdul Nasir</dc:creator>
	<dc:creator>Misran, Misran</dc:creator>
	<dc:creator>Nurdianto, Talqis</dc:creator>
	<dc:subject xml:lang="en-US">Arabic language</dc:subject>
	<dc:subject xml:lang="en-US">ChatGPT</dc:subject>
	<dc:subject xml:lang="en-US">Google Translate</dc:subject>
	<dc:subject xml:lang="en-US">Indonesian-Arabic Translation</dc:subject>
	<dc:subject xml:lang="en-US">Machine translation</dc:subject>
	<dc:subject xml:lang="en-US">Translation quality evaluation</dc:subject>
	<dc:description xml:lang="en-US">This study compares the quality of Indonesian–Arabic academic translations produced by Google Translate and ChatGPT (GPT-4), a topic rarely examined despite widespread MT use in Arabic Language Education programs. Using a qualitative descriptive design with content analysis, the data comprised ten purposively selected undergraduate thesis titles from Indonesian university repositories, including UIN Sunan Kalijaga, UIN Suska Riau, UIN Imam Bonjol Padang, and Universitas Muhammadiyah Makassar. Titles were selected for their academic rigor and need for conceptual precision and formal Arabic register. Translations were analyzed at the phrase level using a Hybrid MQM–Nababan–Baker rubric encompassing seven dimensions: accuracy, acceptability, readability, lexical equivalence, grammatical equivalence, cohesion and coherence, and academic fluency, each rated on a three-point scale. Validity was ensured through alignment with Arabic translation theory, equivalence frameworks, and MQM standards, while iterative consistency checks supported reliability. Results reveal clear differences. ChatGPT achieved an average score of 20.0 out of 21 points (93%), which is classified as Very Good and indicates strong suitability for academic publication. Google Translate scored 13.3 out of 21 points (63%), classified as Good, but requiring post-editing. ChatGPT excelled in contextual meaning, syntactic restructuring, accurate idhafah, case governance, consistent terminology, and scholarly style, whereas Google Translate showed literal transfer. This study enriches AI-assisted translation discourse by grounding evaluation in Arabic translation theory and pedagogy, emphasizing generative AI’s pedagogical potential as a complementary tool while reaffirming the indispensable role of human expertise in maintaining linguistic accuracy, rigor, and academic standards.</dc:description>
	<dc:publisher xml:lang="en-US">UIN Sunan Gunung Djati Bandung</dc:publisher>
	<dc:date>2025-12-25</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.uinsgd.ac.id/index.php/Talim/article/view/51510</dc:identifier>
	<dc:identifier>10.15575/jta.v9i2.51510</dc:identifier>
	<dc:source xml:lang="en-US">Ta'lim al-'Arabiyyah: Jurnal Pendidikan Bahasa Arab &amp; Kebahasaaraban; Vol. 9 No. 2 (2025): Ta'lim al-'Arabiyyah: Jurnal Pendidikan Bahasa Arab dan Kebahasaaraban; 207-223</dc:source>
	<dc:source>2721-5237</dc:source>
	<dc:source>2549-208X</dc:source>
	<dc:source>10.15575/jta.v9i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.uinsgd.ac.id/index.php/Talim/article/view/51510/15745</dc:relation>
	<dc:relation>https://journal.uinsgd.ac.id/index.php/Talim/article/view/51510/15744</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Alfitri Alfitri, Gamal Abdul Nasir Zakaria, Misran Misran, Talqis Nurdianto</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>