Abstract

The NewsREEL challenge provides researchers with an opportunity to evaluate their news recommending algorithms live based on real users’ feedback. Since 2014, participants evaluated a variety of approaches on the Open Recommendation Platform (ORP), yet popularity based algorithms constitute the most successful ones. In this working note, we chronologically describe our participation in NewsREEL online task in the year 2016. With approaches including “most impressed”, “newest”, “most impressed by category”, “content similar” and “most clicked”, we reconfirm that content relevance is not a very good indicator for recommending news. Meanwhile, for the dominating portal Sport1, the extrapolation of the time series of impressions and clicks enables us to predict the items most likely to be clicked in the next hours. A sample analysis on one week data shows us that the duration of an item being popular is much longer than we expected. Thus, we propose that when designing recommenders in this contest, more attention should be paid on the time series patterns of clicks and impressions.

@INPROCEEDINGS{YuanEtAl:2016,
author = {Yuan, Jing and Lommatzsch, Andreas and Kille, Benjamin},
title = {Clicks {P}attern {A}nalysis in {R}eal {S}tream {N}ews {R}ecommender {S}ystems},
booktitle = {{Working Notes of the 7th International Conference of the CLEF Initiative, Evora, Portugal}},
year = {2016},
location = {Evora, Portugal},
pages = {679-690},
issn = {1613-0073},
volume={1609},
publisher = {CEUR Workshop Proceedings},
note = {http://ceur-ws.org/Vol-1609/16090679.pdf}
}