Aplikasi Web untuk Pencepatan Proses Penyaringan Awal KOL dan Influencer Berdasarkan Metrik Engagement Rate

Oktavian, Widya (2026) Aplikasi Web untuk Pencepatan Proses Penyaringan Awal KOL dan Influencer Berdasarkan Metrik Engagement Rate. Tugas Akhir (S1) - thesis, Universitas Bakrie.

[thumbnail of COVER] Text (COVER)
00.Cover.pdf - Accepted Version
Download (597kB)
[thumbnail of BAB I-III] Text (BAB I-III)
01.BAB I-III.pdf - Accepted Version
Restricted to Registered users only
Download (1MB) | Request a copy
[thumbnail of BAB IV] Text (BAB IV)
02.BAB IV.pdf - Accepted Version
Restricted to Registered users only
Download (1MB) | Request a copy
[thumbnail of BAB V] Text (BAB V)
03.BAB V.pdf - Accepted Version
Restricted to Registered users only
Download (118kB) | Request a copy
[thumbnail of BAB DAFTAR PUSTAKA] Text (BAB DAFTAR PUSTAKA)
04.BAB Daftar Pustaka.pdf - Accepted Version
Download (69kB)
[thumbnail of LAMPIRAN] Text (LAMPIRAN)
05.Lampiran.pdf
Restricted to Registered users only
Download (99kB) | Request a copy

Abstract

ABSTRACT Web Application to Streamline the Screening Process Identifying KOLs and Influencers Based on Metrics Engagement Rate The talent data used at Selected Communication is currently stored in presentation rate card files (.ppt or .pptx formats) with non-uniform text layouts and structures, causing searching, information extraction, and candidate filtering to be conducted manually. This manual process is time-consuming and leads to potential informa- tion inconsistencies within the digital agency operational environment. This study aims to design and develop a web-based talent data governance system capable of automatically parsing text data from presentation slides to support the preliminary filtering process at Selected Communication. The system was developed using the Java programming language with the Spring Boot framework, Thymeleaf, and Apache POI library for in-memory PowerPoint file parsing. The system reads and extracts text attributes including social media usernames, follower counts, engagement rates (ER), niches, profile images, and platform rate cards for Instagram and TikTok. Subsequently, a rule-based Deci- sion Tree method is applied to classify talent performance into three priority status levels: Excellent (ER ≥ 5.0%), Fair (3.0% ≤ ER < 5.0%), and Poor (ER < 3.0%). The results indicate that the web application successfully parses and extracts talent data from .pptx files automatically. Black Box functionality testing achieved a 100% success rate, while the Decision Tree algorithm evaluation on 20 test talent samples demonstrated a 100% match rate between manual calculations and system outpu- ts. The implementation of this system effectively accelerates the preliminary talent filtering process, thereby enhancing operational efficiency and supporting Account Executives and KOL Specialists in decision-making. Keywords: PowerPoint parsing, preliminary filtering, Decision Tree, Java Spring Boot, rate card, talent management

Item Type: Thesis (Tugas Akhir (S1) - )
Uncontrolled Keywords: PowerPoint parsing, preliminary filtering, Decision Tree, Java Spring Boot, rate card, talent management
Subjects: Science > Mathematics > Electronic computers. Computer science
Science > Mathematics > Computer software
Thesis > Thesis (S1)
Divisions: Fakultas Teknik dan Ilmu Komputer > Program Studi Informatika
Depositing User: Widya Oktavian
Date Deposited: 05 Oct 2026 01:48
Last Modified: 05 Oct 2026 01:48
URI: https://repository.bakrie.ac.id/id/eprint/15202

Actions (login required)

View Item View Item