ANALISIS SENTIMEN TWITTER MENGGUNAKAN ALGORITMA DEEP NEURAL NETWORK (DNN) TERHADAP OPINI PENGGUNAAN TV DIGITAL

Technology plays an important role in the daily life of modern society, including in television broadcasting. In November 2022, the government implemented a switch from analogue to digital television broadcasting. This change led to various responses and opinions from Twitter social media users regarding the use of digital television. Therefore, sentiment analysis was conducted using the Deep Neural Network (DNN) algorithm, which is one of the Deep Learning algorithms based on human artificial neural networks that can be used for decision making by using parameters on the input layer, number of hidden layers, learning rate value, output layer and number of neurons in each layer and providing variations in the number of hidden layers to test the performance of the model. The sentiment analysis results show that about 62.5% of opinions are positive and 37.5% are negative. In addition, the DNN method is able to achieve an accuracy rate of 97.06% in predicting public opinion sentiment through Twitter social media. This shows that DNN is an effective approach in analyzing public sentiment related to certain topics.

Keywords: Digital Television, Twitter, Deep Neural Network