Electronic Theses and Dissertation

Pemilihan umum tahun 2024 di Indonesia menjadi sorotan utama dalam perkembangan demokrasi, memicu reaksi emosional yang beragam di kalangan masyarakat. Beragam emosi seperti anger, anticipation, disgust, fear, joy, sadness, surprise, dan trust muncul di berbagai platform media sosial, terutama platform X. Penelitian ini menggunakan dataset yang diperolah dengan menggunakan teknik crawling pada platform X. Metode yang digunakan adalah pendekatan NRC Lexicon untuk melabeli emosi dengan memetakan kata-kata yang mengandung emosi dalam teks. Emosi Anger merupakan emosi yang paling dominan dengan persentase mencapai 33.36%. Penelitian ini melibatkan penggunaan model deep learning, yaitu Recurrent Neural Network (RNN) dan Long Short Term Memory (LSTM) untuk mengklasifikasikan emosi dari teks-teks yang dianalisis. Selain itu, penelitian ini juga mengeksplorasi penerapan teknik SMOTE untuk menangani ketidakseimbangan kelas dalam data. Dengan penerapan SMOTE pada model RNN, akurasi yang dicapai adalah 74.47% dan pada model LSTM dengan penerapan SMOTE, akurasi mencapai 90.49%. Model LSTM (tanpa SMOTE) mencapai nilai akurasi sebesar 98.52%, presisi 90.48%, recall 87.48%, dan f1-score 87.48%. Sementara model RNN (tanpa SMOTE) mencapai nilai akurasi 92.52%, presisi 90.48%, recall 85.75%, dan f1-score 87.48%. Perbandingan dengan model RNN menegaskan keunggulan LSTM dalam mengatasi kompleksitas dan pola jangka panjang dalam data teks terstruktur.

The 2024 general election in Indonesia has been a major highlight in the development of democracy, triggering diverse emotional reactions amongst society. Various emotions such as anger, anticipation, disgust, fear, joy, sadness, surprise, and trust appeared on various social media platforms, especially X platform. This research uses datasets obtained using crawling techniques on the X platform. The method used is the NRC Lexicon approach to label emotions by mapping words that contain emotions in the text. Anger emotion is the most dominant emotion with a percentage reaching 33.36%. This research involves the use of deep learning models, namely Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM), to classify emotions from the analyzed texts. In addition, this research also explores the application of the SMOTE technique to handle class imbalance in the data. With the application of SMOTE to the RNN model, the accuracy achieved was 74.47%, and in the LSTM model with the application of SMOTE, the accuracy reached 90.49%. The LSTM model (without SMOTE) achieved an accuracy value of 98.52%, precision 90.48% recall 85.75%, and f1-score 87.48%. While the RNN model (without SMOTE) achieved 92.52% accuracy, 90.48% precision, 85.75% recall, and 87.48% f1-score. The comparison with the RNN model confirms the superiority of LSTM in overcoming complexity and long-term patterns in structured text data. Keyword: General Election, Platform X, Emotion, NRCLexicon, Recurrent Neural Network, Long Short-Term Memory