Effects of Training Datasets on Both the Extreme Learning Machine and Support Vector Machine for Target Audience Identification on Twitter

摘要: The ability to identify or predict a target audience from the increasingly crowded social space will provide company some competitive advantage over other companies. In this paper, we analyze various training datasets, which include Twitter contents of an account owner and its list followers, using features generated in different ways for two machine learning approaches - Extreme Learning Machine (ELM) Support Vector (SVM). Various configurations ELM SVM have been evaluated. results indicate that datasets tweets achieve best performance, relative feature sets. This finding is important may aid researchers developing classifier capable identifying specific group members. assist spend resources more effectively, by sending offers right audience, hence maximize marketing efficiency improve return on investment.