Fredrik Erlandsson is a Lecturer in Computer Science at Blekinge Institute of Technology, Sweden. Fredrik’s research contains a huge amount of data from social media such as Facebook and Twitter etc. He focused on how to understand the behaviors online and further on to predict different online behaviors. Fredrik has been doing his research within the project environment of BigData@BTH.
Social media provides users with services that enable them to interact both globally and instantly. The behaviors on social media can be modeled into interaction networks, which enable network-based and graph-based methods to model and understand the user behaviors.
An additional contribution from the conducted research is a novel method of crawling that extracts all social interactions from Facebook is presented. They have collected 280 million posts in this research from public pages on Facebook using this crawling method. All this from 700 million users. With all this data it’s possible to illustrate interactions between different users.
Furthermore, a proposed method is used and validated for finding initial nodes for information cascade analyzes, and identification of influential users. Based upon the conducted research, it appears that the data mining approach, association rule learning, can be used successfully in identifying in influential user with high accuracy. In addition, the same method can also be used for identifying initial nodes in an information cascade setting, with no significant difference than other network-based methods.
Finally, the privacy-related consequences of posting online is an important area for users to consider. Therefore, mitigating privacy risks contributes to a secure environment and methods to protect user privacy are presented.