Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Social Sciences Insights Journal PEDAMAS (Pengabdian Kepada Masyarakat)
Karyani Damanik, Sri
Unknown Affiliation
Humanities Economics, Econometrics & Finance Education Energy Engineering Health Professions Law, Crime, Criminology & Criminal Justice Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
A TASK-BASED TRAINING PROGRAM TO IMPROVE ACADEMIC WRITING SKILLS AMONG FIRST-YEAR STUDENTS Amelia, Rezki; Gusmirawati, Gusmirawati; Novianti Sari, Reni; Kumalasari, Intan; Ilham Lutfi , M.; Karyani Damanik, Sri
PEDAMAS (PENGABDIAN KEPADA MASYARAKAT) Vol. 4 No. 01 (2026): JANUARI 2026
Publisher : MEDIA INOVASI PENDIDIKAN DAN PUBLIKASI

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Academic writing skills are fundamental competencies that must be mastered by students from the beginning of higher education. However, first-year students commonly encounter various challenges in academic writing, including weak text organization, inappropriate use of academic language, limited argument development, and insufficient understanding of citation practices and academic ethics. This program aimed to strengthen the academic writing skills of first-year university students through a task-based approach. The program employed a service-learning method implemented through participatory stages, including needs analysis, training sessions, step-by-step writing practice, mentoring, and reflective evaluation. Data were collected through observation, analysis of students’ writing tasks, and participant reflections, and were analyzed using a descriptive qualitative approach. The results show a significant improvement in students understanding of academic writing concepts and characteristics, enhanced writing quality in terms of structure, language use, and argumentation, as well as increased awareness of citation practices and academic integrity. In addition, the program positively influenced students’ attitudes and motivation toward academic writing. These findings suggest that academic writing training based on a task-based approach is effective in strengthening first-year students’ academic literacy and has the potential to be developed as a model for fostering academic culture in higher education institutions.
Integration of machine learning in e-commerce: A systematic literature review on consumer behavior prediction and product recommendation Syamsuri, Abd. Rasyid; Arohman, Rifki; Saputra, Muhammad Renaldy; Ikhlash, Muhammad; Damanik, Sri Karyani
Social Sciences Insights Journal Vol. 3 No. 3 (2025): Social Sciences Insights Journal
Publisher : MID Publisher International

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60036/sg7wnx04

Abstract

This systematic literature review examines the integration of machine learning (ML) in e-commerce, focusing on consumer behavior prediction and product recommendation systems. Following PRISMA guidelines, we searched Scopus, Web of Science, IEEE Xplore, and ACM Digital Library, identifying 1,247 records. After screening, 48 peer-reviewed articles (2019-2024) were included. This review makes three novel contributions: (1) a taxonomy of ML algorithms categorizing approaches by function (prediction vs. recommendation) and technique (supervised, unsupervised, deep learning); (2) a comparative analysis of algorithm performance across different e-commerce contexts; and (3) identification of specific research gaps requiring investigation. Findings reveal that hybrid recommendation systems combining collaborative filtering with deep learning achieve superior accuracy (mean improvement of 15-23% over single-method approaches), while gradient boosting methods (XGBoost, LightGBM) demonstrate the highest predictive performance for purchase behavior. Critical challenges include cold-start problems, data sparsity, algorithmic bias, and privacy concerns. We propose an integrative framework mapping ML technique to specific e-commerce applications and identify five priority areas for future research. Limitations include English-language restrictions and potential publication bias toward positive results.
Co-Authors Abd. Rasyid Syamsuri Arohman, Rifki Gusmirawati, Gusmirawati Ilham Lutfi , M. Kumalasari, Intan Muhammad Ikhlash Novianti Sari, Reni Rezki Amelia Saputra, Muhammad Renaldy