News Recommendation in Real-Time - Smart Information Systems: Computational Intelligence for Real-Life Applications - page 174

research topic. User profiles are typically sparse as they interact with few items. We
may consider recommending not for individual users but for groups of similar users.
This idea reflects the notion of certain users sharing similar preferences. For instance,
some users may focus on sports-related news. Hence, news recommender systems
could recommend articles to the group of these users rather than to each individual.
Discovering similarities in highly sparse data represents a major scientific challenge.
Finally, we consider early trend detection as a means to further improve recom-
mendation quality. Imagine that a novel item enters the collection of news articles.
Systems ought to estimate how likely it will attract a lot of interest. If the system
manages to accurately estimate the probability, it will be able to boost interesting
items early. Thus, the system will collect a larger amount of clicks than continuing
to recommend items which users disregard.
Acknowledgments This workwas funded by the Federal Ministry of Economic Affairs and Energy
(BMWi) under funding reference number KF2392313KM2.
References
1. G. Adomavicius, A. Tuzhilin, Toward the next generation of recommender systems: a survey
of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17 (6), 734-749
(2005)
2. G. Adomavicius, A. Tuzhilin, Context-aware recommender systems, in Proceedings of the
2008 ACM Conference on Recommender Systems—RecSys'08 , p. 335 (2008)
3. G. Adomavicius, J. Zhang, Stability of recommendation algorithms. ACM Trans. Inf. Syst.
30 (4), 1-31 (2012)
4. F. Aiolli, Efficient top-n recommendation for very large scale binary rated datasets, in ACM
RecSys , pp. 273-280 (2013)
5. X. Amatriain, Mining large streams of user data for personalized recommendations. ACM
SIGKDD Explor. Newsl. 14 (2), 37 (2013)
6. R. Bell, Y. Koren, Lessons from the Netflix prize challenge. ACMSIGKDDExplor. 9 (2), 75-79
(2007)
7. J. Bennett, S. Lanning, The Netflix prize, in KDDCup , pp. 3-6 (2007)
8. D. Billsus, M.J. Pazzani, Adaptive news access, in The Adaptive Web , Chapter 18, ed. by
P. Brusilovsky, A. Kobsa, W. Nejdl (Springer, New York, 2007), pp. 550-570
9. T. Bogers, A. van den Bosch, Comparing and evaluating information retrieval algorithms
for news recommendation, in Proceedings of the 2007 ACM Conference on Recommender
Systems—RecSys'07 (ACM Press, New York, 2007) p. 141
10. T. Brodt, F. Hopfgartner, Shedding light on a living lab: the CLEF NEWSREEL open recom-
mendation platform, in IIiX'14: Proceedings of Information Interaction in Context Conference
(ACM, 2014), pp. 223-226
11. M. Burke, A. Hornof, E. Nilsen, N. Gorman, High-cost banner blindness: Ads increase per-
ceived workload, hinder visual search, and are forgotten. ACM Trans. Comput.-Hum. Interact.
(TOCHI) 12 (4), 423-445 (2005)
12. I. Cantador, A. Bellogín, P. Castells, News @hand: a semantic web approach to recommending
news. Adapt. Hypermed. Adapt. Web-based Syst. 5149 , 279-283 (2008)
13. I. Cantador, A. Bellogín, P. Castells, Ontology-based personalised and context-aware recom-
mendations of news items, in 2008 IEEE/WIC/ACM International Conference on Web Intelli-
gence and Intelligent Agent Technology (IEEE, 2008), pp. 562-565