Network Analysis of Digital and Social Media

Permanent URI for this collection


Recent Submissions

Now showing 1 - 4 of 4
  • Item
    Bayesian Social Subgraph Generative Models: Social Network Twins using Belief Networks and Ego Behavior Models
    ( 2023-01-03) Naidu, Nagraj ; El-Gayar, Omar
    A key assumption of a Subgraph Generative Model (SUGM) for sparse networks is that a subgraph is independent of lower order subgraphs in a sparse network. This is not entirely true especially for non-sparse networks. Additionally, the generated networks lack the typical properties of a social network because of an assumption of random growth for nodes and edges. Finally, there is no concept for explicit ego choice or bias when connecting to dyadic or triadic relationships. We develop a novel graph generative model referred to as the Bayesian Social Subgraph Generative Model (BASSUGM). We ground the BASSUGM in a proposed sociological model and leverage Bayesian tools like belief networks. We introduce novel concepts like the networks’ macro theme when combines with an ego’s individuality realizes the ego’s intent. We also demonstrate how the social network twin generated with BASSUGM outperforms SUGM for non-sparse, small, social, networks.
  • Item
    Introduction to the Minitrack on Network Analysis of Digital and Social Media
    ( 2023-01-03) Chu, Kar-Hai ; Rosen, Devan ; Barnett, George
  • Item
    Identifying Hidden Communities of Interest with Topic-based Networks: A Case Study of the Community of Philosophers of Science (1930-2017)
    ( 2023-01-03) Malaterre, Christophe ; Lareau, Francis
    Scientific networks are often investigated by means of citation analyses. Yet, interpretation of such networks in terms of semantic (and often disciplinary) content heavily depends on supplementary knowledge, notably about author research specialties. Similar situations arise more generally in many types of social networks whose semantic interpretation relies on supplementary information. Here, author community net-works are inferred from a topic model which provides direct insights into the semantic specificity of the identified “hidden communities of interest” (HCoI). Using a philosophy of science corpus of full-text articles (N=16,917), we investigate its underlying communities by measuring topic profile correlations be-tween authors. A diachronic perspective is built by modeling the research networks over different time-periods and mapping genealogical relationships be-tween communities. The results show a marked in-crease in philosophy of science communities over time and trace the progressive appearance of the specialization areas that structure the field today.
  • Item
    The Role of Followers and Followees in the Adoption of Innovations
    ( 2023-01-03) Atlas, Mor ; Gavious, Arieh ; Ravid, Gilad
    An online social network is a key platform through which innovation diffuses. To learn about innovativeness, we simultaneously investigate two Twitter networks, the relationships network, following-follower relationships, and the activity network, the flow of tweets. Specifically, the innovativeness relations to the networks' indegree and outdegree, the volume of platform use, and the profile's age. The more active and central the user, the earlier the adoption. Innovativeness increases with the number of followers only when at least several of them adopt the innovation. Surprisingly, having more followees is linked to later engagement with the innovation. This association is mediated by the number of adopters' followees. Those who created a Twitter profile later are also more likely to adopt innovations later. This study is novel in distinguishing between the two networks and analyzing their interactions. Its contribution lies in identifying the innovativeness of users in an online social network platform diffusion.