Maryam Mohammadi
Abstract
Analyzing users' emotions with virtual networks has become an effective field in various sciences and its audience is not only company owners and politicians, but also users. In the ...
Read More
Analyzing users' emotions with virtual networks has become an effective field in various sciences and its audience is not only company owners and politicians, but also users. In the meantime, this field has penetrated in urban studies and has been used by urban planners and designers due to its methodology; whether in the form of research that aims solely at emotion analysis or as an integrated layer in research. The aim of this article is to explain this field in the analysis of urban emotions in the form of modeling methods in order to identify the position of this field in urban studies by examining the importance of emotion and the methods of its study in the city. For this purpose, based on an analytical method, the field of emotion analysis is examined and the position of machine learning in measuring it is explained. The data set of this research is related to 8 cities of Iran, which was extracted from Twitter and the textual data analysis was considered. In order to train the machine for sentiment analysis, machine learning and deep learning have been used and their results have been compared. The algorithms used in machine learning are support vector machine, logistic regression and decision tree, and in deep learning, the machine is trained and tested using neural network and hybrid network. Based on the results of deep learning, it has performed better for predicting emotions and text polarity in Iran's big cities and had an accuracy of 80.
