The Evaluation of 5G technology from Sentiment Analysis Perspective in Twitter
Tugkan Seckin, Zeynep Hilal Kilimci · 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) · 2020
Sentiment analysis is the action of explaining the meaning of emotions such as positive, negative, or neutral through various text mining methods and materials. Thus, companies can both focus on target customers and prevent customer churn by taking into account their current customers' opinions about their products with the help of sentiment analysis. In this work, we concentrate on to observe the perception of 5G technology using various machine learning and deep learning algorithms. For this purpose, naive Bayes, support vector machine, and k-nearest neighbour methods are employed as conventional machine learning algorithms. In addition, Recurrent Neural Networks and Long Short-Term Memory Networks as deep learning methodologies are utilized to observe the effect of deep learning models. In order to show the performance of proposed model, 58,965 released tweets with 5G hashtag are gathered from Twitter as English through customized crawler. Experiment results demonstrate the superior classification success of recurrent neural networks in terms of the perception of sentiments of user comments.