Host: The Japanese Society for Artificial Intelligence
Name : The 32nd Annual Conference of the Japanese Society for Artificial Intelligence, 2018
Number : 32
Location : [in Japanese]
Date : June 05, 2018 - June 08, 2018
High-capacity data with various types of information updated frequently is called big data and SNS is also one of them. In recent years, big data has improved research /product service quality and management strategy, etc. This research is aimed at estimating detailed items of persona in marketing, and we propose individual posting from big data in this paper. We propose an individual posting method from big data and hobby analysis method for users. The proposed methods can make it easy to detect the language features and analyze SNS. We apply a Naive Bayes method to create classifiers and estimate their hobbies. The result of estimating their hobbies was an average of about 93% correct answer rate. We discuss that the proposed methods could create their persona
