A Comparison of Fundamental Network Formation Principles Between Offline and Online Friends on Twitter

• Main Authors: NATALI, Felicia, ZHU, Feida
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2016
• Subjects: Network formation; Offline friends; Online friends; Twitter Social network; Offline friends prediction; Machine learning; Offline online; Databases and Information Systems; Social Media
• Online Access: https://ink.library.smu.edu.sg/sis_research/3134; https://ink.library.smu.edu.sg/context/sis_research/article/4134/viewcontent/ComparisonNetworkFormation_Twitter_2016_afv.pdf
• Institution: Singapore Management University

We investigate the differences between how some of the fundamental principles of network formation apply among offline friends and how they apply among online friends on Twitter. We consider three fundamental principles of network formation proposed by Schaefer et al.: reciprocity, popularity, and triadic closure. Overall, we discover that these principles mainly apply to offline friends on Twitter. Based on how these principles apply to offline versus online friends, we formulate rules to predict offline friendship on Twitter. We compare our algorithm with popular machine learning algorithms and Xiewei’s random walk algorithm. Our algorithm beats the machine learning algorithms on average by 15 % in terms of f-score. Although our algorithm loses 6 % to Xiewei’s random walk algorithm in terms of f-score, it still performs well (f-score above 70 %), and it reduces prediction time complexity from O(n2)to O(n).