Measuring node importance on Twitter microblogging
Leila Weitzel
Federal University of Pará
Marabá, Pará, 68501-970, Brazil
+559421017114
lmartins@ufpa.br
Paulo Quaresma
University of Évora
Évora, 7000, Portugal
pq@uevora.pt
José Palazzo M. de Oliveira
Federal University of Rio Grande do Sul
Porto Alegre, Rio Grande do Sul, 91501-
970, Brazil
palazzo@inf.ufrgs.br
ABSTRACT
Social Networks (SN) are created whenever people interact with
other people in online social networks, such as Twitter, Google+,
Facebook and etc. Twitter is a social networking and micro-
blogging service; it creates several new interesting social network
structures. In this sense, our main goal is to investigate the power
of retweet mechanism. The findings suggest that relations of
"friendship" at Twitter are important but not enough. Still, the
centrality measures of a node importance do not show how
important users are. We uncovered some other principles that
must be studied like, homophily phenomenon, the tendency of
individuals to associate and bond with similar others.
Categories and Subject Descriptors
E.1 [Data Structures]: Graphs and network; G.2.2 [Graph
Theory]: graph labeling.
General Terms
Measurement, Human Factors, Verification.
Keywords
Social Network Analysis, Twitter, Retweet, Node Importance.
1. INTRODUCTION
The recent proliferation of web applications and mobile devices
has made online Social Network - SN more accessible than ever
before. People connect with each other beyond geographical and
timeline barriers, diminishing the constraints of physical
boundaries in creating new ties [1].
The recent proliferation of Internet social media applications and
mobile devices has made social connections more accessible than
ever before. In the last few years the number of users of online
social networks like Facebook, MySpace and Twitter gained
considerable popularity and grown at an unprecedented rate [14].
Twitter is a social networking and micro-blogging service. Twitter
allows users to communicate and stays connected through the
exchange of short messages, called tweets. These posts are brief
(up to 140) and can be written or received with a variety of
computing devices, including cell phones.
Twitter creates several interesting social network structures. The
most obvious network is the one created by the “follows” and “is
followed by” relationships without approval, these create a
different type of ties, where the directionality of tie is important
(i.e. who is following whom) [12]. When a user posts a message,
if other users like it, they repost it (or “Retweet” - RT), and a large
number of users can be potentially reached by a particular
message. Based on this context, we looked at the problem through
two perspectives: first, studying topological structure of user´s RT
alter and ego-network, second, ranking nodes based on strength of
RT ties. In particular, we investigate the influence of “retweeting”
mechanism in health context.
The outline of this paper is as follows: Section 2 presents the
background of the research in the context of social network
analysis; Section 3 we explain the data extraction technique and
network modelling approach and data analysis; Section 4 explain
the methodological approach; Section 5 we discuss the results and
future works and Section 6 we present the acknowledgment, and
the last Section the references.
2. RELATED WORK
Human beings have been part of Social Networks - SN since our
earliest days. We are born and live in a world of connections. The
SNs are created whenever people interact with other people.
These ties can characterize any type of relationship, friendship,
authorship, etc. For further details see “Social Network Analysis:
Methods and Applications”, by Wasserman and Faust, the most
usually used reference book [26].
One common type of social analysis is the identification of
communities of users with similar interests, and within such
communities the identification of the most “influential” users.
Efforts have been made to measuring the influence and ranking
users by both their importance as hubs within their community
and by the quality and topical relevance of their post. Some of
these efforts are: [2, 3, 5–9, 11, 13, 15, 17, 18, 21, 23, 24, 27–29].
Most of these researches are based on: follower, tweet and
mention count, co-follower rate (ratio between follower and
following), frequency of tweets/updates, who your followers
follow, topical authorities. Centrality measures such as
Indegree/Outdegree, Eigen Vector, Betweenness, Closeness,
PageRank [20] and others have been used to evaluate node
importance too.
Each one of this metrics evidences a class of issue. For instance,
Betweenness Centrality represents a node that occurs in many
shortest paths among other nodes; this node is called “gatekeeper”
between groups node. Closeness Centrality is the inverse of
Average Distance (geodesic distance). Closeness reveals how long
it takes information to spread from one node to others. Eigen
Centrality measures take into account Hub-centrality (out links)
and Authority-Centrality (in links). According Bonacich [4],
“Eigenvector Centrality can also be seen as a weighted sum of not
only direct connections but indirect connections of every length,
thus, it takes into account the entire pattern in the network.
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for profit or commercial advantage and that
copies bear this notice and the full citation on the first page. To copy
otherwise, to republish, to post on servers or to redistribute to lists,
requires prior specific permission and/or a fee.
WIMS'12, June 13-15, 2012 Craiova, Romania
Copyright © 2012 ACM 978-1-4503-0915-8/12/06... $10.00.