This paper presents an analysis of a temporal network that describes the social connections of a large-scale (similar to 30,000) sample of online social network users, inhabitants of a fixed city. We tested how the main network formation determinants-transitivity, preferential attachment, and social selection-contribute to network evolution. We obtained that tie appearing and tie removing events are governed by different combinations of mechanisms: whereas the structure of the network is responsible for the formation of new ties, nodal nonstructural characteristics "decide" whether a tie will continue to exist. Next, our findings show that only one network formation mechanism, gender selectivity, has a significant impact on both tie appearing and tie removing processes. What is interesting, the effect of gender selectivity is most notable for low-degree vertices. Besides this, our analysis revealed that opinion selectivity appears to be a noticeable (but not very important) factor only in the case of tie removing, whereas its contribution to tie appearing is elusive. Our findings suggest that nodes' activity is a crucial factor of network evolution-the majority of tie removing events can be explained by the age-based activity mechanism. Finally, we report that transitivity and preferential attachment do govern network evolution. However, there are two important details: (i) their zone of influence is restricted primarily by tie appearing and (ii) the preferential attachment mechanism is replaced by the anti-preferential attachment rule if the number of common peers is greater than zero.
