This Author published in this journals
All Journal Catha Saintifica
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PROMOTION COPYWRITING GENERATOR MODELING USING PROBABILISTIC PARSING TECHNIQUE IN NLP: CASE STUDY AT CV. BERKAH TIGA DEWI Mardiyantoro, Nahar; Ngatoilah, Mohamad; Jalia, Kunti Najma; Hidayaturofingah, H
CATHA SAINTIFICA Vol 2 No 1 (2024): May 2024
Publisher : Sentra Kekayaan Intelektual dan Inovasi Teknologi (INOTEK) Universitas Sains Al-Qur'an

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32699/cathasaintifica.v2i1.7632

Abstract

This study aims to develop a promotional copywriting generator model based on the Probabilistic Parsing technique in Natural Language Processing (NLP), applied to CV. Berkah Tiga Dewi, is a snack production and sales company located in Bumirejo Village, Mojotengah District, Wonosobo. The proposed model was evaluated using Precision, Recall, F1-Score, and Perplexity metrics. The results showed a significant increase in the quality of the promotional text, with the F1-Score of the Probabilistic Parsing model reaching 0.86, compared to the traditional method which only reached 0.70. In addition, a lower Perplexity value indicates that the resulting text is more natural and easy to understand. Validation through cross-validation techniques produced a consistent performance with an average Precision of 0.88 and Recall of 0.85. This study proves the effectiveness of the Probabilistic Parsing technique in producing persuasive and relevant copywriting, providing practical solutions to the company's marketing needs. The impacts include increasing product appeal and corporate image. Development prospects include adapting the model to other products and integrating with digital marketing platforms. In conclusion, the research objectives were achieved with relevant and significant results in the practical application of CV. Berkah Tiga Dewi marketing.