Trends in Evolving Networks
The popularity of nodes changes with time, with nodes losing and regaining popularity. We find and show that the recent trend of a node’s popularity is more predictive of future popularity growth. The trendiness factor, i.e., the amount of history needed for calculating this trajectory, is a network-wide characteristic and is different across networks.

Paper: Mokryn, Osnat, Allon Wagner, Marcel Blattner, Eytan Ruppin, and Yuval Shavitt. “The role of temporal trends in growing networks.” PLoS ONE 11, no. 8 (2016): e0156505. (Link)
Enjoy Reading This Article?
Here are some more articles you might like to read next:
- Unleashing the Power of Absence and Surprise
- Lab Celebration: Eran's RecSys 2025 Paper!
- Paper Alert: What Travelers Say vs. What They Rate
- Congratulations to Roi Alfassi — Part of His Master's Thesis Highlighted at HAI-GEN, IUI'2025!
- From Feelings to Fingerprints: A Talk at the Department of Communication Colloquium
- Reflections from the NetSciX'25 Keynote
- Interpretable Transformation and Analysis of Timelines through Learning via Surprisability (LvS)
- Harnessing AI for Creative Collaboration: Insights from Our Brainwriting Study
- Beyond R0: Unraveling COVID-19's Transmission Mysteries Through Temporal Network Analysis
- Talk at TAU's Cyber Week, June 26, 2023