Blog

Barbara Made the News: Mining the Behavior of Crowds for Time-Aware Learning to Rank

WSDM Poster Barbara Made the News
Poster presented at The 9th ACM International Conference on Web Search and Data Mining

In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of commentary and information through multiple mediums, users on the Web interact with and produce new posts about newsworthy topics and give rise to trending topics. This paper proposes to leverage on the behavioral dynamics of users to estimate the most relevant time periods for a topic. Our hypothesis stems from the fact that when a real-world event occurs it usually has peak times on the Web: a higher volume of tweets, new visits and edits to related Wikipedia articles, and news published about the event.

In this paper, we propose a novel time-aware ranking model that leverages on multiple sources of crowd signals. Our approach builds on two major novelties. First, a unifying approach that given query q, mines and represents temporal evidence from multiple sources of crowd signals. This allows us to predict the temporal relevance of documents for query q. Second, a principled retrieval model that integrates temporal signals in a learning to rank framework, to rank results according to the predicted temporal relevance. Evaluation on the TREC 2013 and 2014 Microblog track datasets demonstrates that the proposed model achieves a relative improvement of 13.2% over lexical retrieval models and 6.2% over a learning to rank baseline.

Slides

Full paper presented at The 9th ACM International Conference on Web Search and Data Mining (WSDM 2016), San Francisco, California, USA. February 22-25, 2016. Please cite:

Flávio Martins, João Magalhães, and Jamie Callan. 2016. Barbara Made the News: Mining the Behavior of Crowds for Time-Aware Learning to Rank. In Proceedings of the Ninth ACM International Conference on Web Search and Data Mining (WSDM ’16): 667-676, 2016.

Gravity has a plot twist?

I watched Gravity (2013) at my local cinema in the glorious IMAX 3D format. I was on the edge of my seat throughout and loved every moment. I recommend that you watch Gravity at the cinema if you love science fiction and visual effects!

Gravity is all about Dr. Ryan Stone (Sandra Bullock) and Matt Kowalski (George Clooney). In this mission, Kowalski shares stories with the crew and mission control about his many space missions. He seems very comfortable and reassuring, recounting his stories while gliding through space using a prototype space walk suit. Further into the movie however, he appears a bit different in nature to me.

Spoilers ahead so look away if you have not seen Gravity yet. Watch the trailer instead.

What If… Gravity has a plot twist?

Is Kowalski really the commander of the STS-157 mission? I think there is a chance that he is not even in the mission roster. Maybe he is not even up there. Notice that when Dr. Stone is inside the Soyuz vessel and has decided to quit, Kowalski inexplicably appears  after a long absence and grabs the outside of the Soyuz hatch. We were stunned but we quickly figured out that this sighting of Kowalski is a product of Dr. Stone’s delirious state probably from oxygen deprivation. So, should we accept that “tethered-savior” Kowalski or even mission commander Kowalski were both the real deal?

This being Dr. Stone’s first mission I think we can see Kowalski as her coping mechanism. Kowalski, a veteran astronaut could have been part of Dr.Stone training in the ground, memories which she uses now to overcome fear and  to calm herself down. Do you remember Kowalski’s eagerness to tell stories while gliding in space with his special suit? From the beginning, when she is servicing the Hubble, until they meet in Soyuz he helps her remember all her training, reassuring her on proper breathing to flight training.