Popularity Prediction for Social Media over Arbitrary Time Horizons
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
ACM Conference on Human Factors in Computing Systems (CHI)
Although users generate a large volume of text on Facebook every day, we know little about the topics they choose to talk about, and how their network responds. Using Latent Dirichlet Allocation (LDA), we identify topics from more than half a million Facebook status updates and determine which topics are more likely to receive audience feedback, such as likes and comments.
Furthermore, as previous research suggests that men and women use language for different purposes, we examine gender differences in topics, finding that women tend to share more personal issues (e.g., family matters) and men discuss more general public events (e.g., politics and sports). Post topic predicts how many people will respond to it, and gender moderates the relationship between topic and audience responsiveness.
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga Behram, James Huang, Charles Bai, Michael Gschwind, Anurag Gupta, Myle Ott, Anastasia Melnikov, Salvatore Candido, David Brooks, Geeta Chauhan, Benjamin Lee, Hsien-Hsin S. Lee, Bugra Akyildiz, Max Balandat, Joe Spisak, Ravi Jain, Mike Rabbat, Kim Hazelwood
Jungdam Won, Deepak Gopinath, Jessica Hodgins