Title: "Time-sensitive Personalized Query Auto-Completion"
ABSTRACT
Query auto-completion (QAC) is a popular feature of many modern search engines aimed at enhancing the search experience. Published QAC models often rank QAC candidates according to their past popularity. However, query popularity changes over time and may vary drastically from user to user. Fortunately, previous work has developed both time-sensitive and user-specific QAC methods to obtain better QAC rankings. We report on ongoing work on combining the two aspects: time-awareness and personalization.
Using search logs, we return the top N QAC candidates by predicted popularity based on recent trends and cyclic phenomena, and then rerank the top N candidates based on a user-specific context before outputting the final QAC list. More specifically, we use auto-correlation to detect the query periodicity by means of long-term time-series analysis and anticipate future query popularity based on recent one-week observations. After measuring the similarity between queries in the current search session (or the queries of the same user) and QAC candidates, we finally rerank the QAC candidates. In the talk I will detail the models and report on preliminary experimental results.
The talk is based on joint work with Fei Cai.
BIOGRAPHICAL NOTE
Maarten de Rijke is full professor of Information Processing and Internet in the Informatics Institute at the University of Amsterdam. He holds MSc degrees in Philosophy and Mathematics (both cum laude), and a PhD in Theoretical Computer Science. He worked as a postdoc at CWI, before becoming a Warwick Research Fellow at the University of Warwick, UK. He joined the University of Amsterdam in 1998, and was appointed full professor in 2004.
De Rijke leads the Information and Language Processing Systems group, one of the world's leading academic research groups in information retrieval. During the most recent computer science research assessment exercise, the group achieved maximal scores on all dimensions. His research focus is on intelligent information access, with projects on social media analytics, vertical search engines, machine learning for information retrieval, and semantic search.
A Pionier personal innovational research incentives grant laureate (comparable to an advanced ERC grant), De Rijke has generated over 35MEuro in project funding. With an h-index of 49 he has published over 600 papers, published or edited over a dozen books, is the next Editor-in-Chief of ACM Transactions on Information Systems, (associate) editor for various journals and book series, and a current and former coordinator of retrieval evaluation tracks at TREC, CLEF and INEX. He was co-chair for SIGIR 2013, general chair for ECIR 2014 and will be program co-chair for information retrieval for CIKM 2015.
He is the director of the University of Amsterdam's Intelligent Systems Lab (ISLA), of the Center for Creation, Content and Technology (CCCT), of the Ad de Jonge Center for Intelligence and Security Studies, and of the Amsterdam Data Science Research Center.
The retrieval and language technology developed by his research group is being used by organizations around the Netherlands and beyond, and has given rise to various spin-off initiatives.
mobile