Recent work (Larson, 1996; Gibson et al., 1998; Flake et al., 2000) has attempted to use analysis of link topology to find “web communities". By tapping into these digital representations for users we can learn a great deal about both virtual and real world communities of people.
To predict whether one person is associated with another, we rank all users by their similarity to that person. Our matchmaking algorithm is based on the well-established result in sociology that friends tend to be similar (Feld, 1981; Carley, 1991). Hence the more things two people have in common, the more likely they are to be friends, and the more likely they are to link to each other on their homepages.
0 comentarios:
Publicar un comentario en la entrada