Claim Missing Document
Check
Articles

Found 23 Documents
Search

Interview Result Extraction For Functional Requirements Identification Using TextRank Algorithm Yunianto, Dika Rizky; Putri, Annisa Rahmania; Wijayaningrum, Vivi Nur
Journal of Artificial Intelligence and Software Engineering Vol 6, No 1 (2026): Maret
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i1.8868

Abstract

Functional requirement identification is a critical stage in information system development that determines system alignment with user needs. Interviewing is a dominant technique for eliciting requirements, but interview results in the form of long, unstructured text require significant analysis time and are prone to subjectivity if done manually. This research aims to apply the TextRank algorithm to automatically summarize interview results so that important information can be obtained more concisely. The research was conducted through text preprocessing stages, sentence similarity calculation (word overlap), graph construction, and sentence ranking using the PageRank algorithm. Important sentences were selected based on threshold variations (k = 3, 5, 7, 9). Three methods were compared: standard TextRank, TextRank with TF-IDF weighting, and TextRank with stemming preprocessing. Evaluation used precision, recall, and F1-score metrics against ground truth. Results show that standard TextRank with threshold 7 provided the most balanced performance (F1-score 71.05%), being more stable than TF-IDF based methods for interview data. This algorithm proved effective in improving the efficiency of the functional requirement identification process.
ANALISIS FAKTOR PROJECT BASED LEARNING MELALUI GRAND TEORI S-O-R PADA MANAJEMEN PEMASARAN Suryadi; Joko Samboro; Dika Rizky Yunianto
Jurnal Akuntansi Bisnis dan Humaniora Vol. 10 No. 1 (2023): Jurnal Akuntansi Bisnis dan Humaniora
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jabh.v10i1.4126

Abstract

Changes in the Independent Curriculum Free Learning in the Industrial Revolution Era 4.0 is a challenge for changing the learning paradigm, communicating the affective domain in the Gradation of Attitudes, Knowledge and skills that require the concept of Stimulus Organism Response. Implementation of this learning is a continuation of Blended in type discovery and problem base learning (Suryadi, et al 2020) which shows a very effective impact for project tasks according to industry needs. Project based learning is a scientific learning model that emphasizes students to learn to find and discover for themselves an incomplete concept or principle. The research objective is to analyze the dominant factors of the Marketing Management project base learning model. This research method is "Four-D", the sampling technique uses probability sampling techniques and data collection techniques using observation methods, learning (Project Based Learning), pretest & post test methods, and questionnaire methods. Factor analysis data analysis techniques. Findings of social attitudes, motivation and activity as determinants of achievement for which 75 statements in order of importance (1) Social attitudes of 25 questions with a factor loading value of 0.5 to 0.89 (2) Motivation a number of 12 questions with a loading factor value of between 0.60 to 0.80 (3) The activity of a number of 4 question items with a loading factor value between 0.56 to 0.63. Project Based Learning is suitable for vocational.
TEXT SIMILARITY PADA DOKUMEN PRODUK CERTIPORT DENGAN DOKUMEN PROFIL CALON KLIEN SERTIFIKASI Hilman Zahrawa Budiarto; Dika Rizky Yunianto; Vit Zuraida
Prosiding Seminar Nasional Universitas Ma Chung (Informatika & Sistem Informasi Bahasa dan Seni
Publisher : Ma Chung Press

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

Abstract

Proses profiling kebutuhan sertifikasi calon klien di Certiport Authorized Testing Center (CATC) JTI Polinema yang masih dilakukan secara manual rentan terhadap subjektivitas dan terkendala kesenjangan antara narasi kompetensi calon klien dengan terminologi teknis pada dokumen produk sertifikasi. Penelitian ini bertujuan merancang dan mengimplementasikan sistem rekomendasi sertifikasi otomatis berbasis hybrid text similarity untuk mengukur tingkat kecocokan antara dokumen Objective Domain sertifikasi Certiport dengan dokumen profil calon klien sertifikasi. Sistem dibangun menggunakan arsitektur komputasi hybrid yang mengintegrasikan TF-IDF pada dimensi numerik dan Sentence Transformers model all-MiniLM-L6-v2 pada dimensi semantik, disertai pipeline penerjemahan otomatis untuk menjembatani perbedaan bahasa antara profil calon klien berbahasa Indonesia dengan Objective Domain berbahasa Inggris. Pengujian dilakukan terhadap 16 dokumen profil calon klien sertifikasi dari tiga institusi yang merepresentasikan variasi kebutuhan kompetensi lintas domain. Evaluasi dilakukan menggunakan metrik Precision, Recall, Accuracy, dan F1-Score untuk mengukur kualitas rekomendasi yang dihasilkan sistem. Hasil pengujian menunjukkan performa optimal pada batas rekomendasi Top-20 dengan rasio pembobotan 40% numerik dan 60% semantik, menghasilkan rata-rata Precision sebesar 29,37%, Recall sebesar 40,20%, Accuracy sebesar 74,68%, dan F1-Score sebesar 29,85%. Ablation study membuktikan bahwa pendekatan hybrid meningkatkan F1-Score sebesar 48,9% dibandingkan TF-IDF Only. Pengujian penerimaan pengguna menghasilkan tingkat kelayakan sebesar 88,57%, yang termasuk dalam kategori sangat layak diimplementasikan. Hasil penelitian ini menunjukkan bahwa CertiMatch mampu membantu proses rekomendasi sertifikasi menjadi lebih cepat, konsisten, dan objektif sehingga dapat mendukung pengambilan keputusan dalam proses profiling kebutuhan sertifikasi calon klien.