Determination of Mental States from Texts Using Evolutionary Imperialist Competitive Algorithm and Convolution Neural Networks

Abstract- The aim of this study is to investigate writings to find out the mood of people in typing texts. In this study, 14640 tweets related to airlines were used to analyze emotions in three categories: positive, negative and neutral. The novel proposed approach has three main steps. In the first step, we perform a pre-processing operation to purify the dataset. In the second step, using the Imperialist Competitive Algorithm (ICA), the main keywords from all the existing texts are extracted. Keywords are the words that have the most impact on categorization. Then, a convolution neural network (CNN) is exploited to extract more features. In the last step, classification, using a multilayer perceptron neural network (MLP), is applied. In the proposed new method, unlike the conventional methods in which words go to the next stage after preprocessing, we use the Imperialist Competitive Algorithm to extract the main words from all these words, which in turn causes There is a significant reduction in the volume of input words.using this new proposed approach, we achieved precision, accuracy and recall of 0.990, 0.983 and 0.875, respectively. The experimental results indicated the superiority of the proposed method the comparison with other well-known approaches.