English

Understanding Twitter Engagement with a Click-Through Rate-based Method

Information Retrieval 2020-10-15 v1 Machine Learning Social and Information Networks

Abstract

This paper presents the POLINKS solution to the RecSys Challenge 2020 that ranked 6th in the final leaderboard. We analyze the performance of our solution that utilizes the click-through rate value to address the challenge task, we compare it with a gradient boosting model, and we report the quality indicators utilized for computing the final leaderboard.

Cite

@article{arxiv.2010.06985,
  title  = {Understanding Twitter Engagement with a Click-Through Rate-based Method},
  author = {Andrea Fiandro and Jeanpierre Francois and Isabeau Oliveri and Simone Leonardi and Matteo A. Senese and Giorgio Crepaldi and Alberto Benincasa and Giuseppe Rizzo},
  journal= {arXiv preprint arXiv:2010.06985},
  year   = {2020}
}

Comments

8 pages, 4 figures, 4 tables, Recsys2020 Challenge

R2 v1 2026-06-23T19:20:19.787Z