No reciprocity in "liking" photos: Analyzing like activities in instagram

Jin Yea, Jang Kyungsik Han, Dongwon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Scopus citations


In social media, people often press a "Like" button to indicate their shared interest in a particular content or to acknowledge the user who posted the content. Such activities form relationships and networks among people, raising interesting questions about their unique characteristics and implications. However, little research has investigated such Likes as a main study focus. To address this lack of understanding, based on a theoretical framework, we present an analysis of the structural, influential, and contextual aspects of Like activities from the test datasets of 20 million users and their 2 billion Like activities in Instagram. Our study results first highlight that Like activities and networks increase exponentially, and are formed and developed by one's friends and many random users. Second, we observe that five other essential Instagram elements influence the number of Likes to different extents, but following others will not necessarily increase the number of Likes that one receives. Third, we explore the relationship between LDA-based topics and Likes, characterize two user groups-specialists and generalists- and show that specialists tend to receive more Likes and promote themselves more than generalists. We finally discuss theoretical and practical implications and future research directions.

Original languageEnglish (US)
Title of host publicationHT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery, Inc
Number of pages10
ISBN (Electronic)9781450333955
StatePublished - Aug 24 2015
Event26th ACM Conference on Hypertext and Social Media, HT 2015 - Guzelyurt, Cyprus
Duration: Sep 1 2015Sep 4 2015

Publication series

NameHT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media


Other26th ACM Conference on Hypertext and Social Media, HT 2015

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Cite this