SISTEM PEMBERI UMPAN BALIK TERHADAP JAWABAN WAWANCARA KERJA BERBASIS NATURAL LANGUAGE PROCESSING

Khinthia Sukma Melati Luthfiana, . (2026) SISTEM PEMBERI UMPAN BALIK TERHADAP JAWABAN WAWANCARA KERJA BERBASIS NATURAL LANGUAGE PROCESSING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (750kB)
[img] Text
AWAL.pdf
Download (3MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (7MB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (5MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (14MB)
[img] Text
BAB 5.pdf
Download (673kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (1MB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository staff only
Download (94kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (16MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (292kB)

Abstract

Job interviews, particularly during the recruitment process for State-Owned Enterprises (SOEs), which emphasizes the AKHLAK competency framework, often pose a challenge for job seekers due to a lack of objective feedback for self-evaluation. This study aims to design and develop an automated feedback system for job interview responses based on Natural Language Processing (NLP). The system is designed to assist candidates in effectively evaluating and refining their answers. The Waterfall methodology was employed for system development, incorporating text pre-processing stages to extract Indonesian language features derived from literary sources. Semantic alignment between the user's spoken response and an ideal answer was measured using a combination of Term Frequency-Inverse Document Frequency (TF-IDF), Cosine Similarity, and a synonym mapping technique to overcome the limitations of rigid keyword matching. System testing results, comparing the NLP model's evaluations against assessments by HR experts, yielded a Mean Absolute Deviation (MAD) of 0.38, indicating a low level of deviation and high reliability. Functionality testing via Black Box Testing demonstrated a 100% success rate across all scenarios. Furthermore, User Acceptance Testing (UAT) involving seven respondents resulted in an average satisfaction score of 4.70 out of 5.00 (an index of 96.93%), placing the system in the "Very Good" category. The study concludes that the developed NLP-based system is highly suitable as an interactive interview simulation tool capable of providing contextual, formative feedback to job seekers.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2210511009] [Pembimbing 1: Musthofa Galih Pradana] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Ridwan Raafi'udin] [Penguji 2: Kharisma Wiati Gusti]
Uncontrolled Keywords: Job Interview, Automated Feedback, TF-IDF, Cosine Similarity, AKHLAK BUMN.
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: KHINTHIA SUKMA MELATI LUTHFIANA
Date Deposited: 28 Aug 2026 04:51
Last Modified: 28 Aug 2026 04:51
URI: http://repository.upnvj.ac.id/id/eprint/52060

Actions (login required)

View Item View Item