Promoting Relevant Results in Time-Ranked Mail Search

Mail search has traditionally served time-ranked results, even if it has been shown that relevance ranking provides higher retrieval quality on average. Some Web mail services have recently started to provide relevance ranking options such as the relevance toggle in the search results page of Yahoo Mail, or the ``top results" section in Inbox by Gmail. Yet, ranking results by relevance is not accepted by all, either in mail search, or in in other domains such as social media, where it has even triggered some public outcry. Given the sensitivity of the topic, we propose here to investigate a mixed approach of promoting the most relevant results, to which we refer as ``heroes'', on top of time-ranked results. We argue that this approach represents a good compromise to mail searchers, supporting on one hand the time sorted paradigm they are familiar with, while being almost as effective as full relevance ranking view that Web mail users seem to be reluctant to adopt. We describe three hero-selection algorithms we have devised and the associated experiments we have conducted in Yahoo mail. We measure retrieval success via two metrics: MRR (Mean Reciprocal Rank) and Success@k, and verify agreement between these metrics and users' direct feedback. We demonstrate that supplementing time-sorted results with hero results leads to a higher MRR than the traditional time-sorted view. We additionally show that MRR better reflects users' perception of quality than Success@k. Finally, we report on online results following the successful launch of one of our hero-selection algorithms for all Yahoo enterprise mail users and a few million Yahoo Web mail users.

[1]  Miles Efron,et al.  Estimation methods for ranking recent information , 2011, SIGIR.

[2]  Ilknur Celik,et al.  Leveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter , 2011, SEMWEB.

[3]  References , 1971 .

[4]  Martin Hacker,et al.  Understanding re-finding behavior in naturalistic email interaction logs , 2011, SIGIR '11.

[5]  David Carmel,et al.  Rank by Time or by Relevance?: Revisiting Email Search , 2015, CIKM.

[6]  Brian D. Davison,et al.  Learning to rank for freshness and relevance , 2011, SIGIR.

[7]  Luis Gravano,et al.  Answering General Time-Sensitive Queries , 2008, IEEE Transactions on Knowledge and Data Engineering.

[8]  Gilad Mishne,et al.  Towards recency ranking in web search , 2010, WSDM '10.

[9]  Susan T. Dumais,et al.  Searching to eliminate personal information management , 2006, CACM.

[10]  Geert-Jan Houben,et al.  Twinder: A Search Engine for Twitter Streams , 2012, ICWE.

[11]  Dotan Di Castro,et al.  You've got Mail, and Here is What you Could do With It!: Analyzing and Predicting Actions on Email Messages , 2016, WSDM.

[12]  Vagelis Hristidis,et al.  How fresh do you want your search results? , 2013, CIKM.

[13]  W. Bruce Croft,et al.  Time-based language models , 2003, CIKM '03.

[14]  Susan T. Dumais,et al.  Stuff I've Seen: A System for Personal Information Retrieval and Re-Use , 2003, SIGF.

[15]  Fernando Diaz,et al.  Temporal profiles of queries , 2007, TOIS.

[16]  David Carmel,et al.  The Demographics of Mail Search and their Application to Query Suggestion , 2017, WWW.

[17]  Michael S. Bernstein,et al.  Eddi: interactive topic-based browsing of social status streams , 2010, UIST.

[18]  Yoelle Maarek,et al.  How Many Folders Do You Really Need?: Classifying Email into a Handful of Categories , 2014, CIKM.