作者: Rishi Singh , Rajdeep Niyogi
DOI: 10.1109/ICACCI.2015.7275617
关键词: Politics 、 Social media 、 Internet privacy 、 Classifier (UML) 、 Personality 、 Relevance (information retrieval) 、 General election 、 Computer science 、 Informatics
摘要: Today people use social media (eg, Twitter) to express their views on different topics. Many political parties have utilized such platforms for election campaigns. Twitter data may provide a lot of information about users personality. We study how the personality and interest an individual is linked with his/her associations. used set two (AAP BJP) pertaining 2014 general elections India. obtained 1000 from network around prominent leaders these manually annotated relevant trained it using SVM classifier. The results showed that interest, personality, both considered together relevance in determining associations user, yielding classifier accuracy 0.60.