© 2014 IEEE. Social Networking Service (SNS) is prevailing rapidly in Japan in recent years. The most popular ones are Facebook, mixi, and Twitter, which are utilized in various fields of life together with the convenient tool such as smart-phone. In this work, a questionnaire investigation is carried out in order to clarify the current usage condition, issues and desired functions. More than 1,000 samples are gathered Bayesian network is utilized for this analysis. Sensitivity analysis is carried out by setting evidence to all items. This enables overall analysis for each item We analyzed them by sensitivity analysis and some useful results were obtained. We have presented the paper concerning this. But the volume becomes too large, therefore we have split them and this paper shows the latter half of the investigation result by setting evidence to Bayesian Network parameters. Differences in usage objectives and SNS sites are made clear by the attributes and preference of SNS users. They can be utilized effectively for marketing by clarifying the target customer through the sensitivity analysis.
Aburai, T., & Takeyasu, K. (2014). Overall sensitivity analysis utilizing Bayesian network for the questionnaire investigation on SNS. In 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 (pp. 1274–1279). Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/SCIS-ISIS.2014.7044633