A survey on session detection methods in query logs and a proposal for future evaluation

@article{GayoAvello2009ASO,
  title={A survey on session detection methods in query logs and a proposal for future evaluation},
  author={Daniel Gayo-Avello},
  journal={Inf. Sci.},
  year={2009},
  volume={179},
  pages={1822-1843}
}
Discovering Single-Query Tasks from Search Engine Logs
TLDR
In-depth studies on query logs show that they are not just some words and absolutely they could be useful for some other goals, and query logs can not only analyzed to find out just some simple information about users’ activities but also can use data mining methods to extract knowledge to develop new search-related applications.
Deriving query suggestions for site search
TLDR
This article reports on a systematic study of different query modification methods applied to a substantial query log collected on a local website that already uses an interactive search engine and demonstrates the usefulness of log analysis to extract query modification suggestions.
Distributed Deep Web Search
TLDR
Virtual surfacing is proposed, a new, and in the authors' opinion better, deep web search paradigm which tries to combine the benefits of the two already existing paradigms, surfacing and virtual integration, and which also raises new research opportunities.
Task-Oriented Query Classification
TLDR
This thesis assumes that a query log categorized by tasks is already available and focus on the problem of finding the right task for a new query, which will help the user accomplishing a search task or fulfilling an information need more satisfying.
Identifying Queries in Instant Search Logs
TLDR
A new approach to identifying interactions belonging to the same query in instant query logs is presented, which achieves an F2 score of 0.93 compared to only 0.83 of a state-of-the-art cascading method for query log session detection.
Segmenting User Sessions in Search Engine Query Logs Leveraging Word Embeddings
TLDR
A novel unsupervised method is proposed that improves the current state-of-art inSegmenting user sessions in search engine query logs, leveraging additional heuristics and similarity metrics derived from word embeddings, integrating semantic similarity components that use pre-trained FastText embedding.
The Open University ’ s repository of research publications and other research outputs Deriving query suggestions for site search
TLDR
A systematic study on different query modification methods applied to a substantial query log collected on a local Web site that already employs an interactive search engine to demonstrate the usefulness of log analysis to extract query modification suggestions.
Segmenting Search Query Logs by Learning to Detect Search Task Boundaries
TLDR
This work proposes a model for sequential search log segmentation that uses only query pairs and their time span, generating results suited for on the fly user supporting applications, with improved accuracy over existing search segmentation approaches.
Improved Cascade for Search Mission Detection
TLDR
A new algorithm for session detection based on the state-of-the-art cascading method is presented, which is able to detect multitasking situations as well as search missions and a new corpus of more than 8800 queries manually labeled with search session and mission information is developed.
Suggesting Queries using Query-Flow Graphs to find Dutch Content with Curated Tags
TLDR
It is found that it is possible to apply the query suggestion techniques to a constrained environment, but a trade-off be- tween suggestion usefulness and query coverage is introduced when considering suggestion effectiveness.
...
...

References

SHOWING 1-10 OF 101 REFERENCES
Towards Privacy-Preserving Query Log Publishing
TLDR
A spectrum of approaches are presented along two orthogonal dimensions for anonymizing query logs and whether existing privacy guidelines such as HIPAA can apply to query logs directly, or whether these guidelines require significant adaptation.
Analysis of a very large web search engine query log
TLDR
It is shown that web users type in short queries, mostly look at the first 10 results only, and seldom modify the query, suggesting that traditional information retrieval techniques may not work well for answering web search requests.
Web Usage Mining in Search Engines
TLDR
This chapter focuses on Web usage mining of logs of queries and user clicks to improve search engines and Websites and considers other kinds of Web mining such as link analysis, content mining, or Web dynamics.
User 4XXXXX9: Anonymizing Query Logs
TLDR
This paper proposes two specific solutions (rather than an overly general framework) that attempts to balance the needs of certain types of research while individual privacy, and attempts to deal with sets of queries, that when taken in aggregate, are overly identifying.
Defining a session on Web search engines
TLDR
An analysis of 2,465,145 interactions from 534,507 users of Dogpile.com shows that defining sessions by query reformulation along with Internet Protocol address and cookie provides the best measure, resulting in an 82% increase in the count of sessions.
Query Expansion by Mining User Logs
TLDR
This study proposes a new method for query expansion based on user interactions recorded in user logs that extracts correlations between query terms and document terms by analyzing user logs and can produce much better results than both the classical search method and the other query expansion methods.
Using navigation data to improve IR functions in the context of web search
TLDR
A mixture model for the observed set of search sessions is developed, and variants of the classical EM algorithm for training are proposed, which yields a type of navigation-based query clustering.
Locality in search engine queries and its implications for caching
  • Yinglian XieD. O'Hallaron
  • Computer Science
    Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies
  • 2002
TLDR
This work studies two real search engine traces by examining query locality and its implications for caching, and shows that with proxy or user side caching, prefetching based on the user lexicon looks promising.
Probabilistic query expansion using query logs
TLDR
The experimental results show that the log-based probabilistic query expansion method can greatly improve the search performance and has several advantages over other existing methods.
...
...