Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Do you really want to delete this prezi?
Neither you, nor the coeditors you shared it with will be able to recover it again.
Make your likes visible on Facebook?
Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.
Transcript of RecSys 2014
Cold-start News Recommendation with Domain-dependent BrowseGraph
, L.M. Aiello, R. Schifanella, A. Jaimes
BrowseGraph and Referrer URL
edges are aggregated
add useful information
Yahoo News Browse Graph
2 months of Yahoo News logs
Users' browsing session
from sessions to BrowseGraph
Kendall-tau of Nodes PageRank
structure of the graphs
topics of the news articles
very different size
Jaccard similarity of node sets
short sessions as expected
Referrer Graphs Structure
Nodes Overlap and Importance
Study the Referrer Graphs
[ref] Referrer Graph
[full] Browse Graph
[mix] ref > full
hourly time slots (2 months)
previous hour : build the model
current hour : test set
Browse Graph :
very useful as
indicator of implicit user feedback
Referrer Graphs :
of selecting good candidates
Recommending the next news article
Evaluation : Precision@1
Evaluation : MRR@3
Conclusion and Future Work
common problem that never goes away
general solution : Popularity? CB? Freshness?
user browsing traces
waiting for some user traffic?
(Park and Chu, RecSys 2009; Konstan and Riedl, 2012)
User browsing session
of the web traffic
thousands of new articles per day
short user sessions
(The Guardian, 2012)
(Kumar and Tomkins, SIGIR 2010)
(Tsagkias and Blanco, SIGIR 2012)
can we face the cold-start problem exploiting this information?
This approach could be applied on
type of items
characterization of the user session by the referrer URL
(Chiarandini et al., ICME 2012)
(IP, cookies, etc.)
(does it change by referrer?)
additional methods of node selection