cover
Contact Name
Andy Sapta
Contact Email
saptaandy@gmail.com
Phone
-
Journal Mail Official
lppm_stmik@royal.ac.id
Editorial Address
-
Location
,
INDONESIA
JOURNAL OF SCIENCE AND SOCIAL RESEARCH
Published by Smart Education
ISSN : 26154307     EISSN : 26153262     DOI : -
Journal of Science and Social Research is accepts research works from academicians in their respective expertise of studies. Journal of Science and Social Research is platform to disclose the research abilities and promote quality and excellence of young researchers and experienced thoughts towards Change for Development. The journal releases on February and July.
Arjuna Subject : -
Articles 3,645 Documents
MEMBIAYAI PEMBANGUNAN, MENUTUP KESENJANGAN: ANALISIS SPASIAL DAMPAK BELANJA PENDIDIKAN DAN KESEHATAN TERHADAP IPM KABUPATEN/KOTA DI SUMATERA Muammar Rinaldi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6350

Abstract

Abstract: The Human Development Index (HDI) serves as a critical barometer of local government performance, yet high aggregate scores often conceal stark regional disparities. This study investigates the impact of education and health expenditure on the HDI across 154 regencies and municipalities in Sumatra, Indonesia, during the 2020–2024 period. Employing a quantitative approach with panel data and multiple linear regression analysis using SPSS, the study tests the partial and simultaneous effects of per capita education and health spending on HDI. The results reveal that both education expenditure (β = 0.314; p < 0.05) and health expenditure (β = 0.228; p < 0.05) have a positive and significant effect on HDI, with the model explaining 42.1 percent of HDI variation (Adjusted R² = 0.421). Education spending exerts a relatively stronger influence than health spending. These findings confirm that public social sector investment is vital for human development; however, its effectiveness varies spatially, with regencies in remote and archipelagic areas experiencing diminishing returns. The study contributes to the literature by highlighting that closing development gaps requires not merely increasing budgets, but formulating spatially adaptive fiscal policies tailored to the unique geographical challenges of each region. Keywords: Education expenditure, Health expenditure, Human Development Index, Multiple linear regression, Sumatra.   Abstrak: Indeks Pembangunan Manusia (IPM) merupakan barometer penting kinerja pemerintah daerah, namun capaian agregat yang tinggi seringkali menutupi kesenjangan antar wilayah yang tajam. Penelitian ini bertujuan menganalisis dampak belanja pendidikan dan kesehatan terhadap IPM di 154 kabupaten/kota di Pulau Sumatera selama periode 2020–2024. Menggunakan pendekatan kuantitatif dengan data panel dan analisis regresi linier berganda berbantuan SPSS, studi ini menguji pengaruh parsial dan simultan belanja pendidikan dan kesehatan per kapita terhadap IPM. Hasil penelitian menunjukkan bahwa belanja pendidikan (β = 0,314; p < 0,05) dan belanja kesehatan (β = 0,228; p < 0,05) berpengaruh positif dan signifikan terhadap IPM, dengan model mampu menjelaskan 42,1 persen variasi IPM (Adjusted R² = 0,421). Belanja pendidikan memiliki pengaruh yang relatif lebih kuat dibandingkan belanja kesehatan. Temuan ini mengonfirmasi bahwa investasi publik di sektor sosial sangat vital bagi pembangunan manusia, namun efektivitasnya bervariasi secara spasial, di mana kabupaten/kota di wilayah terpencil dan kepulauan mengalami diminishing returns. Studi ini berkontribusi pada literatur dengan menekankan bahwa menutup kesenjangan pembangunan tidak hanya membutuhkan peningkatan anggaran, melainkan juga kebijakan fiskal yang adaptif secara spasial sesuai dengan tantangan geografis masing-masing daerah. Kata kunci: Belanja pendidikan, belanja kesehatan, Indeks Pembangunan Manusia, regresi linier berganda, Sumatera.
KEPUTUSAN PEMBELIAN E-COMMERCE: PERAN PERCEIVED EASE OF USE, PERCEIVED USEFULNESS DAN ONLINE SHOPPING EXPERIENCE Laras Fitri Aini Hasibuan; Saidun Hutasuhut
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6351

Abstract

Abstract: This study aims to analyze the effect of Perceived Ease of Use, Perceived Usefulness, and Online Shopping Experience on Purchase Decisions in the Lazada application among students of the Faculty of Economics, Universitas Negeri Medan. This research employs a quantitative approach with multiple linear regression analysis. The sample consisted of 128 respondents selected through purposive sampling technique. The results show that Perceived Ease of Use has a positive and significant effect on Purchase Decisions (t = 6.278, sig. = 0.000), while Perceived Usefulness does not significantly affect Purchase Decisions (t = 0.359, sig. = 0.720). Online Shopping Experience has a positive and significant effect on Purchase Decisions (t = 2.154, sig. = 0.033). Simultaneously, all three variables significantly influence Purchase Decisions (F = 84.010, sig. = 0.000) with a coefficient of determination of 66.2%. These findings indicate that ease of application use and quality of online shopping experience are the primary factors driving purchase decisions among students on the Lazada platform. Keywords: purchase decision; perceived ease of use; perceived usefulness; online shopping experience; e-commerce.   Abstrak: Penelitian ini bertujuan untuk menganalisis pengaruh Perceived Ease of Use, Perceived Usefulness, dan Online Shopping Experience terhadap Keputusan Pembelian di aplikasi Lazada pada mahasiswa Fakultas Ekonomi Universitas Negeri Medan. Penelitian menggunakan pendekatan kuantitatif dengan analisis regresi linier berganda. Sampel berjumlah 128 responden yang dipilih melalui teknik purposive sampling. Hasil penelitian menunjukkan bahwa Perceived Ease of Use berpengaruh positif dan signifikan terhadap Keputusan Pembelian (t = 6,278; sig. = 0,000), sedangkan Perceived Usefulness tidak berpengaruh signifikan (t = 0,359; sig. = 0,720). Online Shopping Experience berpengaruh positif dan signifikan terhadap Keputusan Pembelian (t = 2,154; sig. = 0,033). Secara simultan, ketiga variabel berpengaruh signifikan terhadap Keputusan Pembelian (F = 84,010; sig. = 0,000) dengan koefisien determinasi sebesar 66,2%. Temuan ini menunjukkan bahwa kemudahan penggunaan aplikasi dan kualitas pengalaman belanja online merupakan faktor utama yang mendorong keputusan pembelian mahasiswa pada platform Lazada. Kata kunci: keputusan pembelian; perceived ease of use; perceived usefulness; online shopping experience; e-commerce.
PERAN KOMPETENSI DIGITAL, MOTIVASI KERJA, DAN BUDAYA ORGANISASI DALAM MENINGKATKAN KINERJA KARYAWAN Imamul Khaira; Evi Syuriani Harahap
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6352

Abstract

Abstract: This study examines the influence of digital competence, work motivation, and organizational culture on employee performance at PT Yuri Cakra Brothers. A quantitative descriptive approach was applied using multiple linear regression analysis. The population comprised all permanent employees of the company (approximately 120 individuals), with 92 respondents selected through the Slovin formula at a 5% margin of error. Data were collected using a structured Likert-scale questionnaire (1–5) and analyzed with SPSS 26. Prior to hypothesis testing, classical assumption tests, including normality, multicollinearity, and heteroscedasticity tests, were conducted to ensure model validity. The findings indicate that digital competence has a positive and significant effect on employee performance (t = 4.312; p = 0.000). Work motivation also positively and significantly affects employee performance (t = 3.875; p = 0.000). Likewise, organizational culture demonstrates a positive and significant effect (t = 5.127; p = 0.000). Simultaneously, the three independent variables significantly influence employee performance (F = 47.839; p = 0.000). The model yields an Adjusted R² of 0.607, suggesting that 60.7% of the variance in employee performance is explained by digital competence, work motivation, and organizational culture, while the remaining 39.3% is attributable to other factors beyond the scope of this study. Keywords: Digital Competence; Work Motivation; Organizational Culture; Employee Performance   Abstrak: Penelitian ini bertujuan menganalisis pengaruh kompetensi digital, motivasi kerja, dan budaya organisasi terhadap kinerja karyawan di PT Yuri Cakra Brothers. Penelitian menggunakan pendekatan deskriptif kuantitatif dengan analisis regresi linear berganda. Populasi penelitian mencakup seluruh karyawan tetap perusahaan yang berjumlah sekitar 120 orang, dengan sampel sebanyak 92 responden yang ditentukan menggunakan rumus Slovin pada tingkat kesalahan 5%. Data dikumpulkan melalui kuesioner terstruktur menggunakan skala Likert 1–5 dan dianalisis menggunakan SPSS 26. Sebelum pengujian hipotesis, dilakukan uji asumsi klasik yang meliputi uji normalitas, multikolinearitas, dan heteroskedastisitas untuk memastikan kelayakan model. Hasil penelitian menunjukkan bahwa kompetensi digital berpengaruh positif dan signifikan terhadap kinerja karyawan (t = 4,312; p = 0,000). Motivasi kerja juga berpengaruh positif dan signifikan terhadap kinerja karyawan (t = 3,875; p = 0,000). Demikian pula, budaya organisasi menunjukkan pengaruh positif dan signifikan terhadap kinerja karyawan (t = 5,127; p = 0,000). Secara simultan, ketiga variabel independen berpengaruh signifikan terhadap kinerja karyawan (F = 47,839; p = 0,000). Nilai Adjusted R² sebesar 0,607 menunjukkan bahwa 60,7% variasi kinerja karyawan dapat dijelaskan oleh kompetensi digital, motivasi kerja, dan budaya organisasi, sedangkan 39,3% sisanya dipengaruhi oleh faktor lain di luar penelitian ini. Kata kunci: Kompetensi Digital; Motivasi Kerja; Budaya Organisasi; Kinerja Karyawan
PENGEMBANGAN MODUL ANATOMI FISIOLOGI TUBUH MANUSIA BERBASIS PROJECT BASED LEARNING (PJBL) UNTUK MENINGKATKAN HOTS MAHASISWA PENDIDIKAN BIOLOGI Nanda Pratiwi; Finga Fitri Amanda; Nur Hasanah
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6353

Abstract

Abstract: This study aimed to develop, validate, and evaluate the effectiveness of a Project Based Learning (PjBL) based Human Anatomy and Physiology module in improving the Higher Order Thinking Skills (HOTS) of Biology Education students. The study employed a Research and Development (R&D) approach consisting of needs analysis, product design, development, expert validation, revision, and limited implementation stages. The validation process involved two instructional material experts and two subject matter experts using a five-point Likert scale assessment instrument. The effectiveness of the module was tested on 38 Biology Education students using a one-group pretest–posttest design. Data were analyzed using descriptive statistics, N-Gain analysis, and paired-sample t-test. The results indicated that the developed module demonstrated a very high level of feasibility. The instructional material experts awarded an average score of 4.80, while the subject matter experts assigned an average score of 4.74, both categorized as highly feasible. The implementation of the module resulted in an increase in students’ mean scores from 59.55 in the pretest to 79.74 in the posttest. The N-Gain value of 0.45 indicated a moderate improvement, with 68.42% of students achieving moderate to high levels of learning gains. Furthermore, the paired-sample t-test revealed a statistically significant difference between pretest and posttest scores (t = 8.651; p < 0.001). These findings suggest that the developed PjBL-based module is valid, feasible, and effective in enhancing students’ higher-order thinking skills. This study contributes to the development of innovative instructional materials that integrate project-based learning with Human Anatomy and Physiology content to support active learning and the development of 21st-century competencies among pre-service biology teachers. Keywords: Project Based Learning, Instructional Module, Human Anatomy And Physiology, Higher Order Thinking Skills, Biology Education.   Abstrak: Penelitian ini bertujuan untuk mengembangkan, menguji validitas, dan menganalisis efektivitas modul Anatomi Fisiologi Tubuh Manusia berbasis Project Based Learning (PjBL) dalam meningkatkan keterampilan berpikir tingkat tinggi (Higher Order Thinking Skills/HOTS) mahasiswa Pendidikan Biologi. Penelitian menggunakan metode Research and Development (R&D) yang meliputi tahap analisis kebutuhan, perancangan produk, pengembangan, validasi ahli, revisi, dan implementasi terbatas. Validasi dilakukan oleh dua ahli bahan ajar dan dua ahli materi menggunakan instrumen penilaian skala Likert 1–5. Uji efektivitas dilakukan pada 38 mahasiswa Program Studi Pendidikan Biologi melalui desain one-group pretest-posttest. Data dianalisis menggunakan statistik deskriptif, N-Gain, serta uji t berpasangan. Hasil penelitian menunjukkan bahwa modul yang dikembangkan memiliki tingkat kelayakan yang sangat tinggi. Hasil validasi ahli bahan ajar memperoleh skor rata-rata 4,80 dan validasi ahli materi memperoleh skor rata-rata 4,74, yang keduanya termasuk kategori sangat layak. Implementasi modul menunjukkan peningkatan rata-rata skor mahasiswa dari 59,55 pada pretest menjadi 79,74 pada posttest. Hasil analisis N-Gain sebesar 0,45 menunjukkan peningkatan pada kategori sedang, dengan 68,42% mahasiswa mencapai peningkatan pada kategori sedang hingga tinggi. Hasil uji t berpasangan menunjukkan perbedaan yang signifikan antara skor pretest dan posttest (t = 8,651; p < 0,001). Temuan ini mengindikasikan bahwa modul berbasis PjBL yang dikembangkan valid, layak, dan efektif dalam meningkatkan HOTS mahasiswa. Penelitian ini berkontribusi dalam penyediaan bahan ajar inovatif yang mengintegrasikan pembelajaran berbasis proyek dengan materi Anatomi Fisiologi Tubuh Manusia untuk mendukung pembelajaran aktif dan pengembangan kompetensi abad ke-21 pada calon guru biologi. Kata Kunci: Project Based Learning, Modul Pembelajaran, Anatomi Fisiologi Tubuh Manusia, Higher Order Thinking Skills, Pendidikan Biologi.
RANCANG BANGUN PROTOTYPE JEMURAN OTOMATIS MENGGUNAKAN ESP32 DENGAN SENSOR LDR UNTUK MENDETEKSI KONDISI CUACA Yunanri.W.; Iksan Maulana; I Made Widiarta; Eri Sasmita Susanto
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6354

Abstract

Abstract: Unpredictable weather changes often become a problem in the process of drying clothes, especially when it rains suddenly. This condition can cause clothes to get wet again by reducing the efficiency of time and energy. Therefore, this study aims to design and implement a prototype of an automatic clothesline based on the Internet of Things with an ESP32 microcontroller and an LDR sensor as a weather condition detector based on light intensity. The research methods used in this study include hardware and software design, system assembly, and testing the device's performance in various environmental conditions. The LDR sensor is used to read changes in light intensity, then the data is processed by the ESP32 to control the stepper motor as a driver for the automatic opening and closing mechanism of the clothesline. The results of the study show that all system components, including the LDR sensor, ESP32 microcontroller, stepper motor, buzzer, and power supply can work in an integrated and stable manner. This system has a 100% success rate with an average response time of around ±1 second, so it is able to respond to changes in environmental conditions quickly and effectively. Keywords: Prototype, Automatic clothesline, ESP32, LDR Abstrak: Perubahan cuaca yang tidak menentu sering menjadi permasalahan dalam   proses penjemuran pakaian, khususnya ketika hujan turun secara tiba-tiba. Kondisi tersebut dapat menyebabkan pakaian kembali basah dengan menurunkan efisiensi waktu serta tenaga. Oleh karena itu, penelitian ini bertujuan untuk merancang dan mengimplementasikan prototype jemuran pakaian otomatis berbasis Internet Of Things dengan mikrokontroller ESP32 serta sensor LDR sebagai pendeteksi kondisi cuaca berdasarkan intensitas cahaya. Metode penelitian yang digunakan dalam penelitian ini meliputi perancangan perangkat keras dan perangkat lunak, perakitan sistem, serta pengujian kinerja alat di berbagai kondisi lingkungan. Sensor LDR digunakan untuk membaca perubahan intensitas cahaya, kemudian data di proses oleh ESP32 untuk mengendalikan motor stepper sebagai penggerak mekanisme buka dan tutup jemuran secara otomatis. Hasil penelitian menunjukkan bahwa seluruh komponen sistem, meliputi sensor LDR, mikrokontroller ESP32, motor stepper, buzzer, dan catu daya dapat bekerja secara integrasi dan juga secara stabil. Sistem ini memiliki tingkat keberhasilan 100% dengan rata-rata waktu respon sekitar ±1 detik, sehingga mampu merespon perubahan kondisi lingkungan dengan cepat dan efektif. Kata kunci: Prototype, Automatic clothesline, ESP32, LDR
PENGEMBANGAN E-LKPD BERBASIS MODEL THINK TALK WRITE(TTW) BERBANTUAN APLIKASI LIVEWORKSHEETS UNTUKKEMAMPUAN KOMUNIKASI MATEMATIS Rindy Yani; Sri Rahmah Dewi Saragih
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6355

Abstract

The research aims to develop a valid, practical, and effective Think Talk Write (TTW)-based e-LKPD assisted by the Liveworksheets application to improve students' mathematical communication skills in trigonometry. The research is motivated by students' low mathematical communication skills in conveying mathematical ideas, using symbols and notation appropriately, and presenting mathematical representations in problem solving. This study uses the Research and Development (R&D) method with a 4D development model consisting of the Define, Design, Develop, and Disseminate stages. The research subjects are 33 students at Xth-2 class of SMK SMK Swasta Al-Ma'shum Sidodadi. The research instruments consisted of a validation sheet, a teacher and student response questionnaire, and a mathematical communication skills test. The results showed that the developed e-LKPD met the criteria for validity based on the validator's assessment, practicality based on teacher and student responses, and effectiveness with a classical completion rate of 82%. Thus, the TTW-based e-LKPD assisted by Liveworksheets is suitable for use in mathematics learning to help improve students' mathematical communication skills.
PENGARUH MODEL PEMBELAJARAN GAME BASED LEARNING DALAM MENINGKATKAN HASIL BELAJAR SISWA PADA MATA  PELAJARAN EKONOMI KELAS X DI SMA NEGERI 1 PERCUT SEI TUAN TAHUN AJARAN 2025/2026 Sayyidina; Eko Wahyu Nugrahadi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6356

Abstract

Abstract: This study aims to determine the effect of the Game Based Learning model on students' learning outcomes in Economics subjects for Grade X students at SMA Negeri 1 Percut Sei Tuan in the 2025/2026 academic year. This research employed a quasi-experimental method using a pretest-posttest control group design. The population consisted of 356 Grade X students from 10 classes, while the sample included class X-1 as the experimental class and class X-2 as the control class, each consisting of 36 students. Data were collected through observation, interviews, documentation, and tests. Data analysis was conducted using normality tests, homogeneity tests, and hypothesis testing through the Independent Sample T-Test. The results showed that the average posttest score of the experimental class was 86.11, which was higher than that of the control class at 72.56. The hypothesis test yielded a significance value of 0.000 < 0.05, indicating that Ha was accepted and H0 was rejected. These findings demonstrate that the Game Based Learning model has a significant effect on students' learning outcomes. Therefore, the implementation of the Game Based Learning model can be considered an effective alternative for improving students' learning outcomes in Economics subjects. Keywords: Game Based Learning; Learning Outcomes; Economics Education; Quasi Experiment; Innovative Learning.   Abstrak: Penelitian ini bertujuan untuk mengetahui pengaruh model pembelajaran Game Based Learning terhadap hasil belajar siswa pada mata pelajaran Ekonomi kelas X di SMA Negeri 1 Percut Sei Tuan Tahun Ajaran 2025/2026. Penelitian ini menggunakan metode quasi experiment dengan desain pretest-posttest control group design. Populasi penelitian berjumlah 356 siswa kelas X yang terdiri dari 10 kelas, sedangkan sampel penelitian adalah kelas X-1 sebagai kelas eksperimen dan kelas X-2 sebagai kelas kontrol yang masing-masing berjumlah 36 siswa. Teknik pengumpulan data dilakukan melalui observasi, wawancara, dokumentasi, dan tes. Analisis data menggunakan uji normalitas, uji homogenitas, dan uji hipotesis (Independent Sample T-Test). Hasil penelitian menunjukkan bahwa rata-rata nilai posttest kelas eksperimen sebesar 86,11 lebih tinggi dibandingkan kelas kontrol sebesar 72,56. Hasil uji hipotesis memperoleh nilai signifikansi sebesar 0,000 < 0,05, sehingga Ha diterima dan H0 ditolak. Temuan ini menunjukkan bahwa model pembelajaran Game Based Learning berpengaruh signifikan terhadap hasil belajar siswa. Dengan demikian, penerapan model pembelajaran Game Based Learning dapat menjadi alternatif yang efektif dalam meningkatkan hasil belajar siswa pada mata pelajaran Ekonomi. Kata Kunci: Game Based Learning; Hasil Belajar; Ekonomi; Quasi Experiment; Pembelajaran Inovatif.
PEMANFAATAN GENERATIVE AI DALAM MONITORING KESEHATAN TANAMAN Parwito; Eko Sumartono
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6357

Abstract

Abstract: The advancement of generative artificial intelligence (AI) opens new opportunities in precision agriculture, particularly in plant health monitoring and diagnosis. This study aims to systematically review studies discussing the use of Generative AI in plant health monitoring from 2019 to 2024. The method used is a Systematic Literature Review (SLR) following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Searches were conducted on Google Scholar, Scopus, Science Direct, and Portal Garuda databases using defined keywords. Of the 247 identified articles, 38 articles met the inclusion criteria and were analyzed in depth. The results show that Generative AI technologies, especially Generative Adversarial Networks (GAN), Diffusion Models, and vision-based Large Language Models (LLMs), have significantly contributed to plant disease detection, image data augmentation, and agronomic recommendation systems. Disease detection accuracy using GAN-based approaches averaged 94.7%, while visual transformer-based models recorded accuracy up to 96.3%. Key barriers include limited labeled datasets, technology gaps in rural areas, and lack of model adaptation to local Indonesian plant varieties. This study concludes that integrating Generative AI in plant health monitoring systems has great potential but requires multidisciplinary collaboration, local dataset development, and appropriate technology adoption policies. Keywords: Generative AI, GAN, Plant Health, Monitoring, Systematic Literature Review, Precision Agriculture   Abstrak: Perkembangan kecerdasan buatan (AI) generatif membuka peluang baru dalam bidang pertanian presisi, khususnya dalam monitoring dan diagnosis kesehatan tanaman. Penelitian ini bertujuan untuk mengkaji secara sistematis berbagai studi yang membahas pemanfaatan Generative AI dalam monitoring kesehatan tanaman dari tahun 2019 hingga 2024. Metode yang digunakan adalah Systematic Literature Review (SLR) dengan mengikuti protokol PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Pencarian dilakukan pada basis data Google Scholar, Scopus, Science Direct, dan Portal Garuda menggunakan kata kunci yang telah ditetapkan. Dari 247 artikel yang teridentifikasi, sebanyak 38 artikel memenuhi kriteria inklusi dan dianalisis secara mendalam. Hasil kajian menunjukkan bahwa teknologi Generative AI, terutama Generative Adversarial Networks (GAN), Diffusion Model, dan Large Language Model (LLM) berbasis visi, telah memberikan kontribusi signifikan dalam deteksi penyakit tanaman, augmentasi data citra, dan sistem rekomendasi agronomis. Tingkat akurasi deteksi penyakit menggunakan pendekatan berbasis GAN mencapai rata-rata 94,7%, sedangkan model berbasis transformer visual mencatat akurasi hingga 96,3%. Hambatan utama yang ditemukan meliputi keterbatasan dataset berlabel, kesenjangan teknologi di wilayah pedesaan, serta kurangnya adaptasi model terhadap varietas tanaman lokal Indonesia. Penelitian ini menyimpulkan bahwa integrasi Generative AI dalam sistem monitoring kesehatan tanaman memiliki potensi besar namun memerlukan kolaborasi multidisiplin, pengembangan dataset lokal, dan kebijakan adopsi teknologi yang tepat. Kata Kunci: Generative AI, GAN, Kesehatan Tanaman, Monitoring, Systematic
ANALISIS KARIR ALUMNI MENGGUNAKAN RANDOM FOREST DENGAN INTERPRETASI SHAP DAN EVALUASI BIAS MODEL FAIRNESS Irfan Abadi Saragih; Arip Muhridan; Andisyah Putra; Ridwan; Mhd. Ihsan Abidi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 3 (2026): June 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i3.6362

Abstract

  Higher education institutions are required to produce graduates who are competitive in the job market, yet tracer study data is often analyzed only descriptively, leaving deeper patterns unexplored. This study proposes an integrated approach combining Random Forest, SHAP (SHapley Additive exPlanations), and fairness evaluation to analyze alumni career outcomes. Data were sourced from the 2024 tracer study of Universitas Royal, comprising 466 alumni records with a binary target variable indicating employment status. Preprocessing included missing value handling, one-hot encoding, and stratified train-test splitting with an 80:20 ratio. Class imbalance was addressed using the class_weight='balanced' parameter. The Random Forest model achieved an accuracy of 95.7%, F1-score of 0.946, and AUC-ROC of 0.938, significantly outperforming the dummy baseline of 58.5%. Cross-validation across five folds yielded a mean accuracy of 96.4%, confirming model stability. SHAP analysis revealed that features related to educational level appropriateness and relevance of study field to current occupation were the most dominant predictors. Fairness evaluation per study program showed minimal performance disparity between Sistem Informasi (94.7%) and Sistem Komputer (100%), indicating no significant predictive bias. This framework demonstrates that explainable and fair machine learning can serve as a reliable foundation for evidence-based academic policy making
PENGARUH CUSTOMER EXPERIENCE TERHADAP LOYALITAS PELANGGAN DI PT. KAI DIVRE I SUMATERA UTARA Dian Rizky Priyanti Lubis; Arif Fachrian
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 2 (2026): April 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i2.6363

Abstract

Abstract: This study aims to determine the effect of customer experience on customer loyalty at PT. KAI Divre I North Sumatra. This study uses a quantitative approach with a simple linear regression method. The research sample consisted of 209 customers who had used the services of PT. KAI Divre I North Sumatra at least twice, with the sampling technique using the accidental sampling method. The results of the analysis indicate that there is a significant influence between customer experience and customer loyalty. Based on the hypothesis test using simple linear regression, a significance value of p<0.001 (p<0.05) wasa obtained, so the hypothesis in this study was accepted. The regression equation is known as Y=12.051+0.627X, which means that every 1 point increase in the customer experience variable will increase customer loyalty by 0.627. the coefficient of determination (R2) value of 0.753 indicates that customer experience contributes 75.3% to customer loyalty, while 24.7% is influenced by other factors outside the study. The results of the descriptive analysis show that the empirical average of customer loyalty (65.21) is higher than the hypothetical average (47.5), while the empirical average of customer experience (84.72) is also higher than the hypothetical average (62.5). this indicates that customer loyalty is in the medium category, while customer experience is in the high category. Based on these results, it can be concluded that customer experience is a crucial factor in increasing customer loyalty at PT. KAI Divre I North Sumatra.   Keywords: Customer Experience, Customer Loyalty, PT. KAI. Abstrak: Penelitian ini bertujuan untuk mengetahui pengaruh customer experience terhadap loyalitas pelanggan pada PT. KAI Divre I Sumatera Utara. Penelitian ini menggunakan pendekatan kuantitatif dengan metode regresi linear sederhana. Sampel penelitian berjumlah 209 pelanggan yang telah menggunakan layanan PT. KAI Divre I Sumatera Utara minimal dua kali, dengan teknik pengambilan sampel menggunakan metode accidental sampling. Hasil analisis menunjukkan bahwa terdapat pengaruh signifikan antara customer experience terhadap loyalitas pelanggan. Berdasarkan uji hipotesis menggunakan regresi linear sederhana, diperoleh nilai signifikansi p < 0,001 (p < 0,05), sehingga hipotesis dalam penelitian ini diterima. Diketahui persamaan regresi Y = 12,051+0,627X, yang berarti setiap kenaikan 1 poin pada variabel customer experience akan meningkatkan loyalitas pelanggan sebesar 0,627. Nilai koefisien determinasi (R²) sebesar 0,753 menunjukkan bahwa customer experience memberikan kontribusi sebesar 75,3% terhadap loyalitas pelanggan, sedangkan 24,7% dipengaruhi oleh faktor lain di luar penelitian. Hasil analisis deskriptif menunjukkan bahwa rata-rata empiris loyalitas pelanggan (65,21) lebih tinggi dibandingkan rata-rata hipotetik (47,5), sedangkan rata-rata empiris customer experience (84,72) juga lebih tinggi dibandingkan rata rata hipotetik (62,5). Hal ini menunjukkan bahwa loyalitas pelanggan berada pada kategori sedang, sementara customer experience berada pada kategori tinggi. Berdasarkan hasil tersebut, dapat disimpulkan bahwa customer experience merupakan faktor penting dalam meningkatkan loyalitas pelanggan pada PT. KAI Divre I Sumatera Utara.   Kata Kunci: Customer Experience, Loyalitas Pelanggan, PT. KAI