Difficult queries: data analytics, machine learning and users studies

Abstract:

While it exists information on about any topic on the web, international evaluation programs in Information Retrieval have shown that some queries are difficult for systems, which means systems fail to answer to these queries in an effective manner. In this talk I will present various methods that are used in order to try to predict if a query is going to be difficult for the system to answer. I will present some analyses regarding system effectiveness according to system configurations and the link with query difficulty. I then present some machine learning techniques used in order to combine predictors of query difficulty. Finally I will depict some users studies conducted to observe how users perceive query difficulty. I will conclude considering some concrete applications of query difficulty prediction.

Biography:

Josiane Mothe is Professor in computer science at the  Université de Toulouse since 2002. She is a specialist in information retrieval, data mining and big data. From 2012 to 2015, she has been leading the Information System team of the French IRIT lab, CNRS Unit. From 2004 to 2014, she was the editor in chief for Europe and Africa of the international Information Retrieval Journal, (Springer). Since 2011 she is co-responsible of the "MicroBlog contextualization task" at the CLEF evaluation forum. She is now leading the FabSpace 2.0 project, an open innovation network for geodata-driven innovation, funded under H2020 Research and Innovation program.