Parallel Sentimental Analysis Based on Nectar Research Cloud and AURIN

Social networks produce huge amount of complicated and heuristic data, from which the emotion of the owner to particular topics are reflected. Thus, the data can be the source of emotional statistics to analyze the comments related to different topics. In the proposed system, we collected political twitters as the experimental data. The system built a comprehensive structure for data harvesting, NLP, feature selection, machine learning, data mining, database, Restful style API and front-end data visualization, which can be circulated on a cloud system called Nectar research cloud. Besides, the system uses a parallel method to processing data chunk on a super computer called Spartan and discusses the choke point of multiple-core when dealing with the parallel computing. As for data model, Australian Urban Research Infrastructure Network (AURIN), for harvesting some training and test data set is also illustrated in this paper.