Evaluating the importance of different communication types in romantic tie prediction on social media

Matthias Bogaert, Michel Ballings*, Dirk Van den Poel

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


The purpose of this paper is to evaluate which communication types on social media are most indicative for romantic tie prediction. In contrast to analyzing communication as a composite measure, we take a disaggregated approach by modeling separate measures for commenting, liking and tagging focused on an alter’s status updates, photos, videos, check-ins, locations and links. To ensure that we have the best possible model we benchmark 8 classifiers using different data sampling techniques. The results indicate that we can predict romantic ties with very high accuracy. The top performing classification algorithm is adaboost with an accuracy of up to 97.89 %, an AUC of up to 97.56 %, a G-mean of up to 81.81 %, and a F-measure of up to 81.45 %. The top drivers of romantic ties were related to socio-demographic similarity and the frequency and recency of commenting, liking and tagging on photos, albums, videos and statuses. Previous research has largely focused on aggregate measures whereas this study focuses on disaggregate measures. Therefore, to the best of our knowledge, this study is the first to provide such an extensive analysis of romantic tie prediction on social media.

Original languageEnglish
Pages (from-to)501-527
Number of pages27
JournalAnnals of Operations Research
Issue number1-2
Early online date17 Aug 2016
Publication statusPublished - 1 Apr 2018


  • Facebook
  • machine learning
  • online social networks
  • predictive models
  • social media
  • tie strength


Dive into the research topics of 'Evaluating the importance of different communication types in romantic tie prediction on social media'. Together they form a unique fingerprint.

Cite this