Skripsi

KNOWLEDGE DISCOVERY: ANALISIS SENTIMEN DAN EMOSI WHATSAPP BUSINESS DENGAN MACHINE LEARNING DAN DEEP LEARNING

---

WhatsApp Business is one of the platforms that provides direct, fast, and efficient business communication services. This research was conducted to evaluate user perceptions of WhatsApp Business thru an in-depth sentiment analysis and emotion classification approach applied to user reviews. The data used consisted of 3,000 reviews collected thru scraping techniques, which were then processed thru preprocessing stages, labeling based on rating, and manual sentiment classification. Emotion classification uses four categories happy, angry, sad, and afraid. This research implements Machine Learning and Deep Learning models for sentiment analysis. The Machine Learning model uses the TF-IDF method with SVM and Random Forest algorithms, while the Deep Learning model uses a tokenizer for LSTM and CNN algorithms. Based on the evaluation results, the SVM algorithm recorded the highest accuracy of 84.18% in sentiment classification, while the LSTM algorithm showed superiority in terms of precision, recall, and F1-score. This research yielded significant findings as part of the Knowledge Discovery process, namely emotion and sentiment patterns in user reviews that can be used to understand user perceptions more deeply and provide relevant input to developers for improving the quality of Whatsapp Business application services and features.

---

Availability

Detail Information

Series Title

-

Call Number

T1894142025

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 83 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Analisis Sentimen--Machine Learning

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment