Study of Game Theory Mechanism for Effective Sentimental Analysis using Natural Language Processing

摘要

Sentimental analysis of the data being created daily is a challenging task for machine learning and artificial intelligence to understand the human-generated data for further processing using the game theory. In the game theory, both positive and negative instances of the data are needed to understand so that better training can be given for the model using the pre-processed information. The positive and negative instances need to be managed by the model according to the understanding of the model. Machine learning algorithms will work more efficiently if the data is accurate. But the sentimental analysis is needed to understand without the properly aligned data in the proper order or format. The proper arrangement of the data can make a useful model for the game playing prediction. The experiment will give the result of the genre of the game the people are liking to play with respect to both positive and negative instance. The choice of the game will be based on human sentiments. An accuracy of 85% is got in the prediction to verify and predict the game the specific age group will like to opt. Quantum Neural Networks (QNN) is the novel concept to implement in game theory and game playing prediction.