PERBANDINGAN KINERJA RNN-LSTM DAN RANDOM FOREST DALAM ANALISIS SENTIMEN ULASAN APLIKASI CEK BANSOS

WIJAYA, RUDY (2024) PERBANDINGAN KINERJA RNN-LSTM DAN RANDOM FOREST DALAM ANALISIS SENTIMEN ULASAN APLIKASI CEK BANSOS. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 1. cover.pdf Download (256kB) | Preview
Preview	Text (ABSTRAK) 2. ABSTRAK.pdf Download (28kB) | Preview
	Text (BAB I) 3. BAB I.pdf Restricted to Registered users only Download (91kB)
	Text (BAB II) 4. BAB II.pdf Restricted to Registered users only Download (194kB)
	Text (BAB III) 5. BAB III.pdf Restricted to Registered users only Download (113kB)
	Text (BAB IV) 6. BAB IV.pdf Restricted to Registered users only Download (4MB)
	Text (BAB V) 7. BAB V.pdf Restricted to Registered users only Download (76kB)
	Text (DAFTAR PUSTAKA) 8. DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (139kB)
	Text (LAMPIRAN) 9. LAMPIRAN.pdf Restricted to Registered users only Download (839kB)

Abstract

This research evaluates the performance of the RNN-LSTM and Random Forest models in classifying the sentiment of reviews of the Cek Bansos application with a train-test data ratio of 70:30, 80:20, 90:10. The results show that both models have high accuracy (67%-81%). The model is better at classifying the positive class than the negative, with higher precision, recall and f1-score for the positive class. The confusion matrix shows high true negatives and true positives, but the false positives and false negatives are quite significant. Word clouds show differences in the priority of information processed. RNN-LSTM is slightly superior and consistent in accuracy and efficiency.. Keywords: Evaluation of the performance of the RNN-LSTM and Random Forest models, Sentiment analysis of application reviews, Comparison of the accuracy of RNN-LSTM and Random Forest, Division of train-test data in machine learning, Classification of positive and negative class sentiments. Penelitian ini mengevaluasi kinerja model RNN-LSTM dan Random Forest dalam klasifikasi sentimen ulasan aplikasi Cek Bansos dengan rasio data train-test 70:30, 80:20, 90:10. Hasil menunjukkan bahwa kedua model memiliki akurasi tinggi (67%-81%). Model lebih baik mengklasifikasikan kelas positif disbanding negatif, dengan precision, recall, dan f1-score lebih tinggi untuk kelas positif. Confusion matrix menunjukkan true negative dan true positive yang tinggi, tetapi false positive dan false negative cukup signifikan. Word cloud menunjukkan perbedaan dalam prioritas informasi yang diproses. RNN-LSTM sedikit lebih unggul dan konsisten dalam akurasi dan efisiensi. Kata Kunci : Evaluasi kinerja model RNN-LSTM dan Random Forest, Analisis sentimen ulasan aplikasi, Perbandingan akurasi RNN-LSTM dan Random Forest, Pembagian data train-test pada machine learning, Klasifikasi sentimen kelas positif dan negative.

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 24 216
NIM/NIDN Creators:	41519110082
Uncontrolled Keywords:	Evaluasi kinerja model RNN-LSTM dan Random Forest, Analisis sentimen ulasan aplikasi, Perbandingan akurasi RNN-LSTM dan Random Forest, Pembagian data train-test pada machine learning, Klasifikasi sentimen kelas positif dan negative.
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.31 Machine Learning/Pembelajaran Mesin 300 Social Science/Ilmu-ilmu Sosial > 350 Public Administration and Military Science/Administrasi Negara dan Ilmu Kemiliteran > 353 Specific Field of Public Administration/Administrasi Negara yang Membawahi Bidang Khusus, Departemen > 353.5 Administration of Social Welfare/Departemen Sosial (Depsos)
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	28 Sep 2024 03:41
Last Modified:	28 Sep 2024 03:41
URI:	http://repository.mercubuana.ac.id/id/eprint/91911

Actions (login required)

View Item