No abstract

SUMMARYAs a steady new network communications tool, social media have reached global proportions. This phenomenon has had an impact on societies all over the world. Above all, people provide information to Twitter and Facebook on a daily basis. As a result, vast amounts of data exist on Twitter and Facebook, and we can expect to gather useful information from these services. Twitter was changed by the 2011 Tohoku Earthquake. Further, Twitter greatly contributed to the diffusion of information. For example, many users checked on the safety of their friends or family. However, numerous false rumors were spread, probably due to the source of information being unclear. To prepare for future disasters, we must analyze the diffusion of information through social media as soon as possible. In this paper we analyze how the diffusion of information on Twitter has been influenced by structural changes in the network that are caused by communication among users. As a result, just after the 2011 earthquake in the Tohoku region in Japan, it became easier for information to spread in the network. However, this means that misinformation too can spread. We also found that a few users believed misinformation despite being corrected. C⃝ 2015 Wiley Periodicals, Inc. Electron Comm Jpn, 98(9): 1-13, 2015; Published online in Wiley Online Library (wileyonlinelibrary.com).

Discovering the node roles in a network helps to solve diverse social problems. Role discovery attempts to predict the node roles from a network structure, and this method has been extensively studied in various fields. Role discovery using transfer learning has many advantages, but methods using this approach face two kinds of problems: domain-shift problems and model selection. To address these problems, we propose a general framework that includes network representation learning, domain adversarial learning for suppressing domain-shift problems, and model selection without using target labels. As a result of computational experiments, we show on publicly available datasets that the proposed model outperforms conventional methods, the proposed model selection method performs well without using target labels, and the proposed method can be used in real-world datasets. Furthermore, we found that our framework suppressed domain-shift problems, worked well even with differences between networks, and could handle imbalanced classes.

No abstract

No abstract