Co-stardom network

In order to represent any network, it is necessary to characterize the properties of the corresponding graph of nodes and links. Studies on the collaboration network of movie actors have been described in literature such as the work done by Watts and Strogatz (1998)^[2] and Barabási and Albert in 1999^[3] and 2000^{[citation needed]}. The general characteristics are described below.^{[5][6][7][8][9]}

• According to Watts and Strogatz,^[2] the movie-actor network indicated the following characteristics showing a small-world property of the underlying network:

Size: 225 226

Average degree: 61

Average path length: 3.65

Average clustering coefficient: 0.79

Compared to a random graph of the same size and average degree, the average path length is close in value. However, the clustering coefficient is much higher for the movie actor network.

• The network characteristics and scaling exponents given by Barabási and Albert,^[3] indicates the scale-free behavior:

Size: 212 250

Average degree(connectivity): 28.78

Clustering coefficient: 0.79

The network fits a scale-free degree distribution p(k) ~ k^−γ_actor, with an exponent γ_actor = 2.3 ± 0.1.^[3]

• According to Newman, Strogatz and Watts,^[4] the movie actor network can be described by a bipartite graph. Contrary to the studies described previously, they study a bipartite graph with nodes of two types: movies and actors, with links, with edges linking an actor to a movie they appear in. Co-stars are both linked to the same movie they appear in. Therefore, the collaboration graph of film actors can be constructed using a transformation matrix of the bipartite graph interaction matrix.

The Internet Movie Database IMDB represents one of the largest internet sources for movies/actors data, and it is where most of the datasets are collected to study the collaboration network of co-star actors. IMDB facilitates the ability to collect data for very specific and variable types of network. For example, a network can be constructed using data from all the horror movies made within the 2020–2021 timeframe and only picking the top three co-stars in each movie.