SUBAKTI, SATYA (2025) TEXT MINING UNTUK ANALISIS SENTIMEN PRO DAN KONTRA TERHADAP IKN : PERBANDINGAN MODEL DEEP LEARNING LSTM DAN BILSTM. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (579kB) | Preview |
|
![]() |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (49kB) |
|
![]() |
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (302kB) |
|
![]() |
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (134kB) |
|
![]() |
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (455kB) |
|
![]() |
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (29kB) |
|
![]() |
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (94kB) |
|
![]() |
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (792kB) |
Abstract
This study aims to analyze public sentiment—both supportive and opposing— toward the development of Indonesia's new capital city, Ibu Kota Nusantara (IKN), using a Text Mining approach and comparing the performance of two Deep Learning models: Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM). The dataset was collected from the social media platform X (formerly Twitter), capturing real-time public opinions. After undergoing preprocessing to clean the textual data, feature extraction was performed using the Word2Vec technique to capture semantic word meanings. The LSTM and BiLSTM models were then trained to classify sentiment into two primary categories: pro and contra. Model performance was evaluated using accuracy, precision, recall, and F1-score to determine the effectiveness of each approach. The results show that the BiLSTM model outperforms the standard LSTM in classifying public sentiment related to IKN. This research contributes to public policy analysis and provides valuable insights to support strategic decision-making by the government. Kata kunci: Text Mining, Sentiment Analysis, Ibu Kota Nusantara, LSTM, BiLSTM, Word2Vec Penelitian ini bertujuan untuk menganalisis sentimen pro dan kontra masyarakat terhadap pembangunan Ibu Kota Nusantara (IKN) dengan pendekatan Text Mining, serta membandingkan kinerja dua model Deep Learning, yaitu Long Short-Term Memory (LSTM) dan Bidirectional LSTM (BiLSTM). Data dikumpulkan dari media sosial X (sebelumnya Twitter), yang merepresentasikan opini publik secara real-time. Setelah melalui proses praproses teks untuk pembersihan data, fitur teks diekstraksi menggunakan metode Word2Vec guna menangkap makna semantik kata.Model LSTM dan BiLSTM kemudian dilatih untuk mengklasifikasikan sentimen menjadi dua kelas utama pro dan kontra. Evaluasi performa dilakukan menggunakan metrik akurasi, presisi, recall, dan F1- score untuk mengukur efektivitas masing-masing model. Hasil penelitian menunjukkan bahwa model BiLSTM memberikan performa yang lebih baik dibandingkan LSTM dalam mengklasifikasikan sentimen publik terkait IKN. Temuan ini memberikan kontribusi penting bagi analisis opini publik terhadap kebijakan strategis nasional serta dapat dijadikan dasar pertimbangan dalam proses pengambilan keputusan oleh pemerintah. Kata kunci: Text Mining, Analisis Sentimen, Ibu Kota Nusantara, LSTM, BiLSTM, Word2Vec
Actions (login required)
![]() |
View Item |