Deriving query suggestions for site search

Abstract

Modern search engines have been moving away from very simplistic interfaces that aimed at satisfying a user's need with a single-shot query. Interactive features such as query suggestions and faceted search are now integral parts of Web search engines. Generating good query modification suggestions or alternative queries to assist a searcher remains however a challenging issue. Query log analysis is one of the major strands of work in this direction. While much research has been performed on query logs collected on the Web as a whole, query log analysis to enhance search on smaller and more focused collections has attracted less attention, despite its increasing practical importance. In this paper, we report on 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. The purpose of the analysis is to explore different methods for exploiting the query logs to derive new query modification suggestions. We conducted experiments in which we asked users to assess the relevance of potential query modification suggestions that have been constructed using a range of log analysis methods as well as different baseline approaches. The experimental results demonstrate the usefulness of log analysis to extract query modification suggestions. Furthermore, our experiments demonstrate that a more fine-grained approach than grouping search requests into sessions allows to extract better refinement terms from query log files. Finally, locally collected log files are shown to be potentially useful for extracting term relations that are relevant beyond the domain on which they were collected.

External to internal search: Associating searching on search engines with searching on sites

“…Chau, Fang, and Sheng (2005) studied a state governmental website, finding that users behave similarly when using a general-purpose and a website search engine in terms of the average number of terms per query and the average number of result page views per session. Kruschwitz, Lungley, Albakour, and Song (2013) studied university site logs, reporting that users prefer past users' query suggestions, as opposed to content-generated items. Huntington, Nicholas, and Jamali (2007) studied the search engine log files of a news website, noting that the effectiveness of search engine functionality could be evaluated using the number of searches in a session.…”

Generating Query Suggestions to Support Task-Based Search

“…Boldi et al [5] model the query ow in user search sessions via chains of queries. Scenarios in the absence of query logs have been addressed in [4,13], where query suggestions are extracted from the document corpus. However, their focus is on query autocompletion, representing the completed and partial terms in a query.…”

A query suggestion method combining TF-IDF and Jaccard Coefficient for interactive web search

“…[1,4,8,[11][12][13][14][15][16][17][18] Various ontologies have been applied to create knowledge-driven models for generating query suggestions, such as WordNet, [19,20] Wikipedia, [21] ODP and YAGO. [22][23][24][25] Query suggestions can also be generated from query related features extracted from web documents returned by search engines.…”