Semantic homophily in online communication: Evidence from Twitter

Sanja Scepanovic, Igor Mishkovski, Bruno Gonçalves, Trung Hieu Nguyen, Pan Hui

Research output: Contribution to journalArticleScientificpeer-review

Abstract

People are observed to assortatively connect on a set of traits. This phenomenon, termed assortative mixing or sometimes homophily, can be quantified through assortativity coefficient in social networks. Uncovering the exact causes of strong assortative mixing found in social networks has been a research challenge. Among the main suggested causes from sociology are the tendency of similar individuals to connect (often itself referred as homophily) and the social influence among already connected individuals. Distinguishing between these tendencies and other plausible causes and quantifying their contribution to the amount of assortative mixing has been a difficult task, and proven not even possible from observational data. However, another task of similar importance to researchers and in practice can be tackled, as we present here: understanding the exact mechanisms of interplay between these tendencies and the underlying social network structure. Namely, in addition to the mentioned assortativity coefficient, there are several other static and temporal network properties and substructures that can be linked to the tendencies of homophily and social influence in the social network and we herein investigate those.

Concretely, we tackle a computer-mediated communication network (based on Twitter mentions) and a particular type of assortative mixing that can be inferred from the semantic features of communication content that we term semantic homophily. Our work, to the best of our knowledge, is the first to offer an in-depth analysis on semantic homophily in a communication network and the interplay between them. We quantify diverse levels of semantic homophily, identify the semantic aspects that are the drivers of observed homophily and show insights in its temporal evolution. By analyzing these mechanisms we increase understanding on what are the semantic aspects that shape and how they shape the human computer-mediated communication. In addition, our analysis framework presented on this concrete case can be easily adapted, extended and applied on other type of social networks and for different types of homophily.
Original languageEnglish
Pages (from-to)1-18
Number of pages18
JournalOnline Social Networks and Media
Volume2
DOIs
Publication statusPublished - 2017
MoE publication typeA1 Journal article-refereed

Keywords

  • Homophily
  • Semantics
  • Influence
  • Semantic relatedness
  • Twitter
  • Wikipedia
  • Social network analysis
  • Computational social science

Fingerprint

Dive into the research topics of 'Semantic homophily in online communication: Evidence from Twitter'. Together they form a unique fingerprint.

Cite this