Authors:
Andreas Kanavos
;
Isidoros Perikos
;
Ioannis Hatzilygeroudis
and
Athanasios Tsakalidis
Affiliation:
University of Patras, Greece
Keyword(s):
Community Analysis, Graph Mining, Influential Community Detection, Sentiment Analysis, Tweet Emotion Recognition, User Influence.
Related
Ontology
Subjects/Areas/Topics:
Social Media Analytics
;
Society, e-Business and e-Government
;
Web Information Systems and Technologies
Abstract:
The analysis of social networks is a very challenging research area. A fundamental aspect concerns the detection
of user communities, i.e. the organization of vertices in clusters, with many edges joining vertices of
the same cluster and comparatively few edges joining vertices of different clusters. Detecting communities
is of great importance in sociology, biology as well as computer science where systems are often represented
as graphs. In this paper we present a novel methodology for community detection based on users’ emotional
behavior. The methodology analyzes user’s tweets in order to determine their emotional behavior in Ekman
emotional scale. We define two different metrics to count the influence of produced communities. Moreover,
the weighted version of a modularity community detection algorithm is utilized. Our results show that our
proposed methodology creates influential enough communities.