Modeling Link Recommendations as a Network Growth Mechanism and their Impact on Social Contagion

Link recommendation algorithms significantly shape online social networks, in-fluencing both their structural evolution and critical processes such as informa-tion and behavior spread. This paper investigates how these algorithms affectsimple and complex contagion processes by modeling recommendations as addi-tional network growth mechanisms. We introduce a synthetic network model thatintegrates preferential attachment, triadic closure, and choice homophily, then ex-tend it with various link recommenders, including heuristics and graph neural net-works (GNNs). Our findings show that while simple contagions exhibit relativelymodest shifts under most recommenders, complex contagions are highly sensitiveto clustering- and homophily-based recommendations, thriving at moderate rec-ommendation strengths but sharply diminishing under excessive recommendationstrength. These results underscore the nuanced interplay between network struc-ture, recommendation strength, and contagion dynamics, highlighting the impor-tance of incorporating social contagions into the design of link recommendationalgorithms