Detail

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

What is happening now propagates quickly through the Web and prompts users on the Web to interact with and produce new posts about newsworthy topics giving rise to trending topics in social-media platforms. We propose to leverage on this behavioral dynamics 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. We propose a novel time-aware ranking model that leverages on multiple sources of crowd signals and integrates temporal signals in a learning to rank framework to rank results according to the predicted temporal relevance.
Our approach builds on two major novelties. First, a unifying approach that given a query q represents its temporal evidence mined 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.
This presentation is based on a paper accepted to WSDM 2016.