Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika SOROT: Jurnal Pengabdian Kepada Masyarakat
Haddad Alwi Yafie
Telkom University
Civil Engineering, Building, Construction & Architecture Computer Science & IT Engineering Mechanical Engineering Other

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

Found 2 Documents
Search

 1 
Building Productive Students, Program Pelatihan Komunikasi Dasar bagi SMK Telesandi Bekasi Yumna Zahran Ramadhan; Muhammad Solehuddin; Widang Muttaqin; Muhammad Aziz Kurniawan; Yudiansyah; Haddad Alwi Yafie; Nabil Marsya Azzahra; Ananda Alif Raditya; Muhammad Raihan Fadani; Sherly Nur Sausanindra
SOROT : Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 1 (2026): Januari
Publisher : Fakultas Teknik dan Ilmu Komputer (FASTIKOM) UNSIQ

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32699/t1yyqs48

Abstract

Program pengabdian masyarakat ini bertujuan memperkuat keterampilan komunikasi interpersonal dan intrapersonal siswa SMK Telesandi Bekasi sebagai bekal menghadapi tuntutan akademik dan dunia kerja. Kegiatan dirancang untuk menjawab kebutuhan sekolah dalam membangun soft skills yang melengkapi kompetensi teknis siswa di era digital. Metode pelaksanaan meliputi workshop komunikasi, penerapan gamifikasi, serta pendampingan mentor yang melibatkan guru, alumni, dan praktisi. Tahapan program diawali dengan survei kebutuhan melalui kuesioner, wawancara, dan observasi untuk memetakan kemampuan awal siswa. Berdasarkan hasil tersebut, materi pelatihan disusun secara terstruktur mencakup refleksi diri, pengelolaan emosi, public speaking, diskusi kelompok, dan simulasi komunikasi dunia kerja. Implementasi gamifikasi seperti kuis interaktif, leaderboard, dan sistem badge digunakan untuk meningkatkan motivasi dan partisipasi siswa. Evaluasi dilakukan melalui penilaian keterampilan, observasi keaktifan, dan kuesioner kepuasan peserta. Hasilnya menunjukkan peningkatan kepercayaan diri, kemampuan menyampaikan gagasan. Secara keseluruhan, kegiatan ini memberikan dampak positif dan relevan bagi peningkatan mutu pembelajaran serta penguatan budaya komunikasi produktif di sekolah.
Academic Chatbot for Campus Information Services Using Retrieval-Augmented Generation Haddad Alwi Yafie; Achmad Udin Zailani; Widang Muttaqin; Muhammad Sheva Atallah Daffansyah; Muhammad Rafi Ramzi
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16088

Abstract

University service centers handle many repetitive queries about academic schedules, registration, and policies stored in internal documents. Manual lookup is inefficient, and answers given by staff can be inconsistent. Rule-based chatbots only handle limited question patterns, while large language models are hard to update and may produce unsupported answers (hallucinations). This research designs an academic chatbot that combines document retrieval with answer generation so that each answer remains traceable to its source. The system extracts text from campus documents, segments it, encodes it using a multilingual embedding model, and stores it in a vector index for context retrieval. A response is generated through an instruction template that confines the output to the retrieved information and includes page references. Evaluation followed a mixed-method design: a quantitative layer measured retrieval quality (Precision@5, Recall@5) and generation quality using the four RAGAS sub-metrics (faithfulness, answer_relevancy, context_precision, context_recall) on a 100-question test set, while a qualitative layer applied thematic analysis to open-ended user comments. Statistical testing used McNemar's test for accuracy and a paired bootstrap (10,000 resamples) for retrieval metrics; 95% confidence intervals are reported. Results: the proposed RAG system achieved 84% answer accuracy (95% CI 76–90%), Precision@5 = 0.80 and Recall@5 = 0.72, with a System Usability Scale (SUS) score of 78 and a Net Promoter Score (NPS) of +32 from 30 participants. Differences in accuracy versus the lexical and LLM-only baselines were statistically significant (McNemar p < 0.05). The system offers a replicable instantiation of RAG for transparent, citation-backed campus information services in Indonesian.
Co-Authors Achmad Udin Zailani Ananda Alif Raditya Muhammad Aziz Kurniawan Muhammad Rafi Ramzi Muhammad Raihan Fadani Muhammad Sheva Atallah Daffansyah Muhammad Solehuddin Muttaqin, Widang Nabil Marsya Azzahra Sherly Nur Sausanindra Yudiansyah Yumna Zahran Ramadhan