PENGEMBANGAN MODEL FILTERISASI TEKS DENGAN ALGORITMA BOYER-MOORE PADA PROTOTIPE PLATFORM KOMUNIKASI PERSONAL

Pandu Utomo, . (2025) PENGEMBANGAN MODEL FILTERISASI TEKS DENGAN ALGORITMA BOYER-MOORE PADA PROTOTIPE PLATFORM KOMUNIKASI PERSONAL. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (834kB)
[img] Text
AWAL.pdf
Download (822kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (303kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (657kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (264kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (259kB)
[img] Text
RIWAYAT HDUP.pdf
Restricted to Repository UPNVJ Only
Download (101kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (16MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (21MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (3MB)

Abstract

In the increasingly open era of digital communication, it is essential to maintain interactions within ethical and normative boundaries, especially through content moderation to prevent the spread of inappropriate language. This study examines the implementation of the Boyer-Moore algorithm in a prototype web-based personal communication platform for detecting and blocking offensive terms. The algorithm matches user input against a predefined list of inappropriate words using a pattern-matching approach based on heuristic shifts. However, test results indicate that the Boyer-Moore algorithm alone has limited accuracy (12.5%), although it offers very fast processing times (approximately 0.023 seconds per check). This suggests that Boyer-Moore is less effective in handling variations of inappropriate words. In contrast, the Fuzzy Regex algorithm achieves higher accuracy (62.5%) with slightly slower processing (around 0.048 seconds). By combining Boyer-Moore, Fuzzy Regex, normalization techniques, and overlap handling, the system achieves significantly improved detection accuracy of up to 95.8% with an average processing time of 0.095 seconds. These findings suggest that Boyer-Moore functions better as a supporting component within a more comprehensive and adaptive filtering system, rather than as a standalone solution.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511007] [Pembimbing: Jayanta] [Penguji 1: Bayu Hananto] [Penguji 2: I Wayan Rangga Pinastawa]
Uncontrolled Keywords: In the increasingly open era of digital communication, it is essential to maintain interactions within ethical and normative boundaries, especially through content moderation to prevent the spread of inappropriate language. This study examines the implementation of the Boyer-Moore algorithm in a prototype web-based personal communication platform for detecting and blocking offensive terms. The algorithm matches user input against a predefined list of inappropriate words using a pattern-matching approach based on heuristic shifts. However, test results indicate that the Boyer-Moore algorithm alone has limited accuracy (12.5%), although it offers very fast processing times (approximately 0.023 seconds per check). This suggests that Boyer-Moore is less effective in handling variations of inappropriate words. In contrast, the Fuzzy Regex algorithm achieves higher accuracy (62.5%) with slightly slower processing (around 0.048 seconds). By combining Boyer-Moore, Fuzzy Regex, normalization techniques, and overlap handling, the system achieves significantly improved detection accuracy of up to 95.8% with an average processing time of 0.095 seconds. These findings suggest that Boyer-Moore functions better as a supporting component within a more comprehensive and adaptive filtering system, rather than as a standalone solution.
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: PANDU UTOMO
Date Deposited: 06 Aug 2025 03:31
Last Modified: 06 Aug 2025 03:31
URI: http://repository.upnvj.ac.id/id/eprint/37747

Actions (login required)

View Item View Item