Characterizing Email Search using Large-scale Behavioral Logs and Surveys

@article{Ai2017CharacterizingES,
  title={Characterizing Email Search using Large-scale Behavioral Logs and Surveys},
  author={Qingyao Ai and S. Dumais and Nick Craswell and Daniel J. Liebling},
  journal={Proceedings of the 26th International Conference on World Wide Web},
  year={2017}
}
As the number of email users and messages continues to grow, search is becoming more important for finding information in personal archives. In spite of its importance, email search is much less studied than web search, particularly using large-scale behavioral log analysis. In this paper we report the results of a large-scale log analysis of email search and complement this with a survey to better understand email search intent and success. We characterize email search behaviors and highlight… Expand
Understanding and Modeling Success in Email Search
TLDR
An opt-in client application is built which monitors a user's email search activity and then pops up an in-situ survey when a search session is finished, and generative models (MarkovChain of success) of success can predict the session-level success of email search better than baseline heuristics and discriminative models. Expand
Exploring User Behavior in Email Re-Finding Tasks
TLDR
This work proposes a novel framework that provides a realistic way of simulating email re-finding tasks in a crowdsourcing environment using the workers' personal email data, and shows that user behavior can be significantly impacted as a result of the quality of the search ranker, but only when differences in quality are very pronounced. Expand
The Lifetime of Email Messages: A Large-Scale Analysis of Email Revisitation
TLDR
It is found that most emails have a short lifetime, with more than 33% having a lifetime of less than 5 minutes and deleting is the most common action taken on messages visited once, and that responding and organizing are more common for messages visited more than once. Expand
Mining information interaction behavior : Academic papers and enterprise emails
TLDR
This thesis uncovers how academic searchers interact with information objects, and focuses on how users read their enterprise emails, and characterize user reading time, which improves understanding of user behavior on email platforms. Expand
A Comparative Analysis of Web Search Query: Informational Vs. Navigational Queries
TLDR
Compared the informational and navigational type of a web search query that is mostly used in academic settings, the results indicated that the informational search query performed best because several keywords have been included to properly explain the queries. Expand
Characterising dataset search - An analysis of search logs and data requests
TLDR
A systematic study of the patterns and specific attributes that data consumers use to search for data and how it compares with general web search and a study of data requests found that geospatial and temporal attributes are the most common features. Expand
Semantic Location in Email Query Suggestion
TLDR
A simple but effective model that can use location to predict queries for a user even before they type anything into a search box is presented, and which learns effectively even when not all queries have location information. Expand
An Empirical Study of Software Exceptions in the Field using Search Logs
TLDR
This is the first large scale study to analyze how Web search is used to find information about exceptions and identifies most frequent, most effort-intensive, or less successful exceptions and popularity of community Q&A sites. Expand
Characterizing and Predicting Email Deferral Behavior
TLDR
It is found that users are more likely to defer emails when handling them involves replying, reading carefully, or clicking on links and attachments, and a classifier is trained for predicting whether a recently triaged email is actually deferred. Expand
Reply With: Proactive Recommendation of Email Attachments
TLDR
A weakly supervised learning framework for recommending attachable items to the user and a novel strategy for generating labels from an email corpus---without the need for manual annotations---that can be used to train and evaluate the query formulation model are presented. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 37 REFERENCES
Large scale query log analysis of re-finding
TLDR
There is a rich opportunity for search engines to take advantage of re-finding behavior as a means to improve the search experience through analysis of three large-scale data sources: query logs, Web browsing logs, and a daily Web crawl. Expand
Large-Scale Analysis of Email Search and Organizational Strategies
TLDR
A large-scale log analysis of the activities that people perform on email mes-sages (accessing external information via links or attachments, responding to messages, and organizing messages), their search behavior, and their organizational practices in a popular web email client finds that within search sessions, people are more likely to access information and respond to messagers but less likely to organize. Expand
Exploring Query Patterns in Email Search
TLDR
A detailed analysis of email search behaviour obtained from a study of 47 users uncovers a number of behavioral patterns that contrast with those previously observed in web search. Expand
Information re-retrieval: repeat queries in Yahoo's logs
TLDR
It is demonstrated that changes to search engine results can hinder re-finding, and a way to automatically detect repeat searches and predict repeat clicks is provided. Expand
Rank by Time or by Relevance?: Revisiting Email Search
TLDR
It is demonstrated that the default time-driven ranking of Yahoo mail search results can be significantly improved in terms of both recall and precision, by taking into consideration time recency and textual similarity to the query, as well as mail-specific signals such as users' actions. Expand
Using Contextual Information to Improve Search in Email Archives
TLDR
This paper finds that query models based on contextual information improve retrieval effectiveness, and explores the use of thread, mailing list, and community content levels, by expanding the original query with term from these sources. Expand
Am I wasting my time organizing email?: a study of email refinding
TLDR
This work instrumented a modern email client that supports search, folders, tagging and threading, and carried out a field study of 345 long-term users who conducted over 85,000 refinding actions to support opportunistic access. Expand
Understanding user goals in web search
TLDR
A framework for understanding the underlying goals of user searches is described and the experience in using the framework to manually classify queries from a web search engine is illustrated. Expand
Understanding re-finding behavior in naturalistic email interaction logs
TLDR
Using the approaches developed, interesting aspects of email re-finding behavior that have so far been impossible to study are uncovered, such as how various features of email-clients are used in re- finding and the difficulties people encounter when using these. Expand
Rethinking email message and people search
TLDR
This work inspects the email headers of all messages a user has ever sent or received and it creates simple per-contact summaries, including simple information about the message exchange history, the domain of the sender or even the sender's gender. Expand
...
1
2
3
4
...