Presenting a New Sentiment Analysis Method Based on Multi-objective Archimedes Optimization Algorithm and Machine Learning

With the expansion and popularity of social networks among people, special attention has been focused on the activities, reactions, and feelings of people in these networks compared to other circles. Analyzing this volume of unstructured textual information of users requires new and optimal methods of text mining and natural language processing. The purpose of sentiment analysis is to examine a large volume of opinions about an entity by the machine and provide a summarized report of the sentiment expressed in it to the user. To achieve this goal, statistical techniques, data mining, and natural language processing are used. In this article, a new method based on Archimedes' optimization algorithm is presented so that users' opinions can be obtained in less time and with higher accuracy. Also, in order to eliminate one of the main challenges in sentiment analysis, in the feature extraction phase, all ironic sentences are collected and entered into the collection as sentences with a specific class, in order to eliminate this big challenge. This method can be applied to different languages and tries to increase the accuracy and speed of previous algorithms. The evaluation results of the data set show that the proposed method has an accuracy of 0.967.