On the role of conductance, geography and topology in predicting hashtag virality

Published in Social Network Analysis and Mining Journal, Springer, 2015

Recommended citation: Siddharth Bora, Harvineet Singh, Anirban Sen, Amitabha Bagchi, and Parag Singla. "On the role of conductance, geography and topology in predicting hashtag virality." Social Network Analysis and Mining 1, no. 5 (2015): 1-15. http://www.cse.iitd.ac.in/~parags/papers/rcgtphv-snam15.pdf

Changes in network structure during the spread of the topic has been found to be predictive of its eventual reach. We investigate new network-based features such as conductance of topic sub-graph for the task of predicting virality of a hashtag in Twitter. We find that the proposed set of features significantly outperform earlier work. This provides further evidence and motivation to study graph-theoretic properties such as conductance of topic sub-graphs in understanding future spread of the topics.

arXiv link

Bibtex:

@article{bora2015role,
  title={On the role of conductance, geography and topology in predicting hashtag virality},
  author={Bora, Siddharth and Singh, Harvineet and Sen, Anirban and Bagchi, Amitabha and Singla, Parag},
  journal={Social Network Analysis and Mining},
  volume={1},
  number={5},
  pages={1--15},
  year={2015}
}