[ { "key": "V6CH7ENM", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/V6CH7ENM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/V6CH7ENM", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/G7EEQRXB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "V6CH7ENM", "version": 1, "parentItem": "G7EEQRXB", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2011-04-15T08:08:13Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1835457&type=pdf&CFID=18072029&CFTOKEN=90998535", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Liu and Belkin - 2010 - Personalizing information retrieval for multi-sess.pdf", "md5": "4f5e0dbb8b211b36379b8f6d8e18a667", "mtime": 1302854895808, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:08:13Z", "dateModified": "2011-04-15T08:08:41Z" } }, { "key": "4SD3S4ZI", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/4SD3S4ZI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/4SD3S4ZI", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/G7EEQRXB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "4SD3S4ZI", "version": 1, "parentItem": "G7EEQRXB", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2011-04-15T08:08:10Z", "url": "http://portal.acm.org/citation.cfm?id=1835457", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1302854890744, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:08:10Z", "dateModified": "2011-04-15T08:08:41Z" } }, { "key": "G7EEQRXB", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/G7EEQRXB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/G7EEQRXB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Liu and Belkin", "parsedDate": "2010", "numChildren": 2 }, "data": { "key": "G7EEQRXB", "version": 1, "itemType": "conferencePaper", "title": "Personalizing information retrieval for multi-session tasks: the roles of task stage and task type", "creators": [ { "creatorType": "author", "firstName": "Jingjing", "lastName": "Liu" }, { "creatorType": "author", "firstName": "Nicholas J", "lastName": "Belkin" } ], "abstractNote": "Dwell time as a user behavior has been found in previous studies to be an unreliable predictor of document usefulness, with contextual factors such as the user's task needing to be considered in its interpretation. Task stage has been shown to influence search behaviors including usefulness judgments, as has task type. This paper reports on an investigation of how task stage and task type may help predict usefulness from the time that users spend on retrieved documents, over the course of several information seeking episodes. A 3-stage controlled experiment was conducted with 24 participants, each coming 3 times to work on 3 sub-tasks of a general task, couched either as \"parallel\" or \"dependent\" task type. The full task was to write a report on the general topic, with interim documents produced for each sub-task. Results show that task stage can help in inferring document usefulness from decision time, especially in the parallel task. The findings can be used to increase accuracy in predicting document usefulness and accordingly in personalizing search for multi-session tasks.", "proceedingsTitle": "Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "26–33", "series": "SIGIR '10", "seriesNumber": "", "DOI": "10.1145/1835449.1835457", "ISBN": "978-1-4503-0153-4", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "Geneva, Switzerland", "shortTitle": "Personalizing information retrieval for multi-session tasks", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "ACM ID: 1835457", "tags": [ { "tag": "contextual factors in ir", "type": 1 }, { "tag": "design", "type": 1 }, { "tag": "dwell time", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:08:08Z", "dateModified": "2011-04-15T08:08:08Z" } }, { "key": "WFKKETR9", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/WFKKETR9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/WFKKETR9", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/FE3FGFFI", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "WFKKETR9", "version": 1, "parentItem": "FE3FGFFI", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2011-04-15T08:07:24Z", "url": "http://portal.acm.org/citation.cfm?id=1357242", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1302854845208, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:07:24Z", "dateModified": "2011-04-15T08:07:46Z" } }, { "key": "FE3FGFFI", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/FE3FGFFI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/FE3FGFFI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Morris et al.", "parsedDate": "2008", "numChildren": 1 }, "data": { "key": "FE3FGFFI", "version": 1, "itemType": "conferencePaper", "title": "SearchBar: a search-centric web history for task resumption and information re-finding", "creators": [ { "creatorType": "author", "firstName": "Dan", "lastName": "Morris" }, { "creatorType": "author", "firstName": "Meredith", "lastName": "Ringel Morris" }, { "creatorType": "author", "firstName": "Gina", "lastName": "Venolia" } ], "abstractNote": "Current user interfaces for Web search, including browsers and search engine sites, typically treat search as a transient activity. However, people often conduct complex, multi-query investigations that may span long durations and may be interrupted by other tasks. In this paper, we first present the results of a survey of users' search habits, which show that many search tasks span long periods of time. We then introduce SearchBar, a system for proactively and persistently storing query histories, browsing histories, and users' notes and ratings in an interrelated fashion. SearchBar supports multi-session investigations by assisting with task context resumption and information re-finding. We describe a user study comparing use of SearchBar to status-quo tools such as browser histories, and discuss our findings, which show that users find SearchBar valuable for task reacquisition. Our study also reveals the strategies employed by users of status-quo tools for handling multi-query, multi-session search tasks.", "proceedingsTitle": "Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1207–1216", "series": "CHI '08", "seriesNumber": "", "DOI": "10.1145/1357054.1357242", "ISBN": "978-1-60558-011-1", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "Florence, Italy", "shortTitle": "SearchBar", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "ACM ID: 1357242", "tags": [ { "tag": "human factors", "type": 1 }, { "tag": "persistent search", "type": 1 }, { "tag": "search process", "type": 1 }, { "tag": "web history", "type": 1 }, { "tag": "web search interfaces", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:07:23Z", "dateModified": "2011-04-15T08:07:23Z" } }, { "key": "MVPECEP5", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/MVPECEP5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/MVPECEP5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Kellar et al.", "parsedDate": "2006-01-01", "numChildren": 0 }, "data": { "key": "MVPECEP5", "version": 1, "itemType": "journalArticle", "title": "A Goal‐based Classification of Web Information Tasks", "creators": [ { "creatorType": "author", "firstName": "Melanie", "lastName": "Kellar" }, { "creatorType": "author", "firstName": "Carolyn", "lastName": "Watters" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Shepherd" } ], "abstractNote": "While researchers have been studying user activity on the Web since its inception, there remains a lack of understanding of the high level tasks in which users engage on the Web. We have recently conducted a field study in which participants were asked to annotate all web usage with a task description and categorization. Based on our analysis of participants' recorded tasks during the field study, as well as previous research, we have developed a goal-based classification of information tasks which describes user activities on the Web.", "publicationTitle": "Proceedings of the American Society for Information Science and Technology", "publisher": "", "place": "", "date": "2006/01/01", "volume": "43", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "1-22", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/meet.14504301121", "citationKey": "", "url": "http://onlinelibrary.wiley.com/doi/10.1002/meet.14504301121/abstract", "accessDate": "2011-04-15T08:05:00Z", "PMID": "", "PMCID": "", "ISSN": "1550-8390", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Wiley Online Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:05:00Z", "dateModified": "2011-04-15T08:05:00Z" } }, { "key": "QMB7NFM5", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/QMB7NFM5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/QMB7NFM5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Jansen et al.", "parsedDate": "2007-04-01", "numChildren": 0 }, "data": { "key": "QMB7NFM5", "version": 1, "itemType": "journalArticle", "title": "Defining a session on Web search engines", "creators": [ { "creatorType": "author", "firstName": "Bernard J", "lastName": "Jansen" }, { "creatorType": "author", "firstName": "Amanda", "lastName": "Spink" }, { "creatorType": "author", "firstName": "Chris", "lastName": "Blakely" }, { "creatorType": "author", "firstName": "Sherry", "lastName": "Koshman" } ], "abstractNote": "Detecting query reformulations within a session by a Web searcher is an important area of research for designing more helpful searching systems and targeting content to particular users. Methods explored by other researchers include both qualitative (i.e., the use of human judges to manually analyze query patterns on usually small samples) and nondeterministic algorithms, typically using large amounts of training data to predict query modification during sessions. In this article, we explore three alternative methods for detection of session boundaries. All three methods are computationally straightforward and therefore easily implemented for detection of session changes. We examine 2,465,145 interactions from 534,507 users of Dogpile.com on May 6, 2005. We compare session analysis using (a) Internet Protocol address and cookie; (b) Internet Protocol address, cookie, and a temporal limit on intrasession interactions; and (c) Internet Protocol address, cookie, and query reformulation patterns. Overall, our analysis 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. Regardless of the method used, the mean session length was fewer than three queries, and the mean session duration was less than 30 min. Searchers most often modified their query by changing query terms (nearly 23% of all query modifications) rather than adding or deleting terms. Implications are that for measuring searching traffic, unique sessions may be a better indicator than the common metric of unique visitors. This research also sheds light on the more complex aspects of Web searching involving query modifications and may lead to advances in searching tools.", "publicationTitle": "Journal of the American Society for Information Science and Technology", "publisher": "", "place": "", "date": "2007/04/01", "volume": "58", "issue": "6", "section": "", "partNumber": "", "partTitle": "", "pages": "862-871", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/asi.20564", "citationKey": "", "url": "http://onlinelibrary.wiley.com/doi/10.1002/asi.20564/abstract", "accessDate": "2011-04-15T08:04:16Z", "PMID": "", "PMCID": "", "ISSN": "1532-2890", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Wiley Online Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:04:16Z", "dateModified": "2011-04-15T08:04:16Z" } }, { "key": "NESV6TI2", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/NESV6TI2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/NESV6TI2", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/V84X3T8P", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "NESV6TI2", "version": 1, "parentItem": "V84X3T8P", "itemType": "attachment", "linkMode": "imported_url", "title": "ScienceDirect Snapshot", "accessDate": "2011-04-15T08:02:38Z", "url": "http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6VC8-4PMT5X4-2&_user=9056232&_coverDate=05%2F31%2F2008&_rdoc=1&_fmt=high&_orig=gateway&_origin=gateway&_sort=d&_docanchor=&view=c&_searchStrId=1719185972&_rerunOrigin=scholar.google&_acct=C000043701&_version=1&_urlVersion=0&_userid=9056232&md5=ba2957041518af1c57491a5cf55912bc&searchtype=a", "note": "", "contentType": "", "charset": "", "filename": "Jansen et al. - 2008 - Determining the informational, navigational, and t", "md5": "eb87cf47150fb8a2d8e577bcf3ec7b2e", "mtime": 1302854561415, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:02:38Z", "dateModified": "2011-04-15T08:03:10Z" } }, { "key": "F9QKMCC5", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/F9QKMCC5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/F9QKMCC5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/V84X3T8P", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "F9QKMCC5", "version": 1, "parentItem": "V84X3T8P", "itemType": "attachment", "linkMode": "imported_url", "title": "ScienceDirect Full Text PDF", "accessDate": "2011-04-15T08:02:32Z", "url": "http://www.sciencedirect.com/science?_ob=MImg&_imagekey=B6VC8-4PMT5X4-2-1&_cdi=5948&_user=9056232&_pii=S030645730700163X&_origin=gateway&_coverDate=05%2F31%2F2008&_sk=999559996&view=c&wchp=dGLzVzz-zSkWA&md5=a661457d865805aca960fe1a2c2a8112&ie=/sdarticle.pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Jansen et al. - 2008 - Determining the informational, navigational, and t.pdf", "md5": "ea72c21dcb4236e325f630592a66f697", "mtime": 1302854554108, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:02:32Z", "dateModified": "2011-04-15T08:03:10Z" } }, { "key": "V84X3T8P", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/V84X3T8P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/V84X3T8P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Jansen et al.", "parsedDate": "2008-05", "numChildren": 2 }, "data": { "key": "V84X3T8P", "version": 1, "itemType": "journalArticle", "title": "Determining the informational, navigational, and transactional intent of Web queries", "creators": [ { "creatorType": "author", "firstName": "Bernard J.", "lastName": "Jansen" }, { "creatorType": "author", "firstName": "Danielle L.", "lastName": "Booth" }, { "creatorType": "author", "firstName": "Amanda", "lastName": "Spink" } ], "abstractNote": "


In this paper, we define and present a comprehensive classification of user intent for Web searching. The classification consists of three hierarchical levels of informational, navigational, and transactional intent. After deriving attributes of each, we then developed a software application that automatically classified queries using a Web search engine log of over a million and a half queries submitted by several hundred thousand users. Our findings show that more than 80% of Web queries are informational in nature, with about 10% each being navigational and transactional. In order to validate the accuracy of our algorithm, we manually coded 400 queries and compared the results from this manual classification to the results determined by the automated method. This comparison showed that the automatic classification has an accuracy of 74%. Of the remaining 25% of the queries, the user intent is vague or multi-faceted, pointing to the need for probabilistic classification. We discuss how search engines can use knowledge of user intent to provide more targeted and relevant results in Web searching.

", "publicationTitle": "Information Processing & Management", "publisher": "", "place": "", "date": "May 2008", "volume": "44", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "1251-1266", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.ipm.2007.07.015", "citationKey": "", "url": "http://www.sciencedirect.com/science/article/B6VC8-4PMT5X4-2/2/cf258d9e8a14d18e0261d8c91581dde1", "accessDate": "2011-04-15T08:02:30Z", "PMID": "", "PMCID": "", "ISSN": "0306-4573", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ScienceDirect", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Search engines", "type": 1 }, { "tag": "User intent", "type": 1 }, { "tag": "Web queries", "type": 1 }, { "tag": "Web searching", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:02:30Z", "dateModified": "2011-04-15T08:02:30Z" } }, { "key": "IBNJ4QZQ", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/IBNJ4QZQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/IBNJ4QZQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/TJPSEQEN", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "IBNJ4QZQ", "version": 1, "parentItem": "TJPSEQEN", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2011-04-15T07:58:53Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1458163&type=pdf&CFID=18072029&CFTOKEN=90998535", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Boldi et al. - 2008 - The query-flow graph model and applications.pdf", "md5": "32d4389b3a40df4d2ee48be1e5acf969", "mtime": 1302854336929, "tags": [], "relations": {}, "dateAdded": "2011-04-15T07:58:53Z", "dateModified": "2011-04-15T08:01:46Z" } }, { "key": "KS676746", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/KS676746", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/KS676746", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/TJPSEQEN", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "KS676746", "version": 1, "parentItem": "TJPSEQEN", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2011-04-15T07:58:52Z", "url": "http://portal.acm.org/citation.cfm?id=1458163", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1302854333124, "tags": [], "relations": {}, "dateAdded": "2011-04-15T07:58:52Z", "dateModified": "2011-04-15T08:01:46Z" } }, { "key": "RC4WH4P5", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/RC4WH4P5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/RC4WH4P5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/9D8Q5T6K", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "RC4WH4P5", "version": 1, "parentItem": "9D8Q5T6K", "itemType": "attachment", "linkMode": "imported_url", "title": "Improving Automatic Query Classification via Semi-Supervised Learning", "accessDate": "2011-04-15T08:01:27Z", "url": "http://www.computer.org/portal/web/csdl/doi/10.1109/ICDM.2005.80", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "ICDM.2005.html", "md5": null, "mtime": 1302854488531, "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:01:27Z", "dateModified": "2011-04-15T08:01:46Z" } }, { "key": "9D8Q5T6K", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/9D8Q5T6K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/9D8Q5T6K", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Beitzel et al.", "parsedDate": "2005", "numChildren": 2 }, "data": { "key": "9D8Q5T6K", "version": 1, "itemType": "conferencePaper", "title": "Improving Automatic Query Classification via Semi-Supervised Learning", "creators": [ { "creatorType": "author", "firstName": "Steven M.", "lastName": "Beitzel" }, { "creatorType": "author", "firstName": "Eric C.", "lastName": "Jensen" }, { "creatorType": "author", "firstName": "Ophir", "lastName": "Frieder" }, { "creatorType": "author", "firstName": "David D.", "lastName": "Lewis" }, { "creatorType": "author", "firstName": "Abdur", "lastName": "Chowdhury" }, { "creatorType": "author", "firstName": "Aleksander", "lastName": "Kołcz" } ], "abstractNote": "Accurate topical classification of user queries allows for increased effectiveness and efficiency in general-purpose web search systems. Such classification becomes critical if the system is to return results not just from a general web collection but from topic-specific back-end databases as well. Maintaining sufficient classification recall is very difficult as web queries are typically short, yielding few features per query. This feature sparseness coupled with the high query volumes typical for a large-scale search service makes manual and supervised learning approaches alone insufficient. We use an application of computational linguistics to develop an approach for mining the vast amount of unlabeled data in web query logs to improve automatic topical web query classification. We show that our approach in combination with manual matching and supervised learning allows us to classify a substantially larger proportion of queries than any single technique. We examine the performance of each approach on a real web query stream and show that our combined method accurately classifies 46% of queries, outperforming the recall of best single approach by nearly 20%, with a 7% improvement in overall effectiveness.", "proceedingsTitle": "Data Mining, IEEE International Conference on", "conferenceName": "", "publisher": "IEEE Computer Society", "place": "Los Alamitos, CA, USA", "date": "2005", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "42-49", "series": "", "seriesNumber": "", "DOI": "http://doi.ieeecomputersociety.org/10.1109/ICDM.2005.80", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Computer Society", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2011-04-15T08:01:27Z", "dateModified": "2011-04-15T08:01:27Z" } }, { "key": "GTBE2R6Q", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/GTBE2R6Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/GTBE2R6Q", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/9D8Q5T6K", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "GTBE2R6Q", "version": 1, "parentItem": "9D8Q5T6K", "itemType": "note", "note": "Complete PDF document was either not available or accessible. Please make sure you're logged in to the digital library to retrieve the complete PDF document.", "tags": [], "relations": {}, "dateAdded": "2011-04-15T08:01:27Z", "dateModified": "2011-04-15T08:01:27Z" } }, { "key": "TJPSEQEN", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/TJPSEQEN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/TJPSEQEN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Boldi et al.", "parsedDate": "2008", "numChildren": 2 }, "data": { "key": "TJPSEQEN", "version": 1, "itemType": "conferencePaper", "title": "The query-flow graph: model and applications", "creators": [ { "creatorType": "author", "firstName": "Paolo", "lastName": "Boldi" }, { "creatorType": "author", "firstName": "Francesco", "lastName": "Bonchi" }, { "creatorType": "author", "firstName": "Carlos", "lastName": "Castillo" }, { "creatorType": "author", "firstName": "Debora", "lastName": "Donato" }, { "creatorType": "author", "firstName": "Aristides", "lastName": "Gionis" }, { "creatorType": "author", "firstName": "Sebastiano", "lastName": "Vigna" } ], "abstractNote": "Query logs record the queries and the actions of the users of search engines, and as such they contain valuable information about the interests, the preferences, and the behavior of the users, as well as their implicit feedback to search engine results. Mining the wealth of information available in the query logs has many important applications including query-log analysis, user profiling and personalization, advertising, query recommendation, and more. In this paper we introduce the query-flow graph, a graph representation of the interesting knowledge about latent querying behavior. Intuitively, in the query-flow graph a directed edge from query qi to query qj means that the two queries are likely to be part of the same \"search mission\". Any path over the query-flow graph may be seen as a searching behavior, whose likelihood is given by the strength of the edges along the path. The query-flow graph is an outcome of query-log mining and, at the same time, a useful tool for it. We propose a methodology that builds such a graph by mining time and textual information as well as aggregating queries from different users. Using this approach we build a real-world query-flow graph from a large-scale query log and we demonstrate its utility in concrete applications, namely, finding logical sessions, and query recommendation. We believe, however, that the usefulness of the query-flow graph goes beyond these two applications.", "proceedingsTitle": "Proceeding of the 17th ACM conference on Information and knowledge management", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "609–618", "series": "CIKM '08", "seriesNumber": "", "DOI": "10.1145/1458082.1458163", "ISBN": "978-1-59593-991-3", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "Napa Valley, California, USA", "shortTitle": "The query-flow graph", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "ACM ID: 1458163", "tags": [ { "tag": "algorithms", "type": 1 }, { "tag": "communications applications", "type": 1 }, { "tag": "data mining", "type": 1 }, { "tag": "query flow graph", "type": 1 }, { "tag": "query recommendation", "type": 1 }, { "tag": "session segmentation", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2011-04-15T07:58:50Z", "dateModified": "2011-04-15T07:58:50Z" } }, { "key": "THX8VC6W", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/THX8VC6W", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/THX8VC6W", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/J8MJ94T7", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } } }, "data": { "key": "THX8VC6W", "version": 1, "parentItem": "J8MJ94T7", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2011-04-15T07:52:51Z", "url": "http://portal.acm.org/citation.cfm?id=1458176", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1302853972200, "tags": [], "relations": {}, "dateAdded": "2011-04-15T07:52:51Z", "dateModified": "2011-04-15T07:53:33Z" } }, { "key": "6MWPFT2I", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/6MWPFT2I", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/6MWPFT2I", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/43311/items/J8MJ94T7", "type": "application/json" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6MWPFT2I", "version": 1, "parentItem": "J8MJ94T7", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2011-04-15T07:52:53Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1458176&type=pdf&CFID=18072029&CFTOKEN=90998535", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Jones and Klinkner - 2008 - Beyond the session timeout automatic hierarchical.pdf", "md5": "05d302ca5421bfdbd6210cc9f566f93e", "mtime": 1302853976895, "tags": [], "relations": {}, "dateAdded": "2011-04-15T07:52:53Z", "dateModified": "2011-04-15T07:53:33Z" } }, { "key": "J8MJ94T7", "version": 1, "library": { "type": "group", "id": 43311, "name": "Query-Session-Task", "links": { "alternate": { "href": "https://www.zotero.org/groups/query-session-task", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/43311/items/J8MJ94T7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/query-session-task/items/J8MJ94T7", "type": "text/html" } }, "meta": { "createdByUser": { "id": 108784, "username": "geckorello", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/geckorello", "type": "text/html" } } }, "creatorSummary": "Jones and Klinkner", "parsedDate": "2008", "numChildren": 2 }, "data": { "key": "J8MJ94T7", "version": 1, "itemType": "conferencePaper", "title": "Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs", "creators": [ { "creatorType": "author", "firstName": "Rosie", "lastName": "Jones" }, { "creatorType": "author", "firstName": "Kristina Lisa", "lastName": "Klinkner" } ], "abstractNote": "Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or session, a timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real sessions manually labeled into hierarchical tasks, and show that timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum precision of only 70%. We report on properties of this search task hierarchy, as seen in a random sample of user interactions from a major web search engine's log, annotated by human editors, learning that 17% of tasks are interleaved, and 20% are hierarchically organized. No previous work has analyzed or addressed automatic identification of interleaved and hierarchically organized search tasks. We propose and evaluate a method for the automated segmentation of users' query streams into hierarchical units. Our classifiers can improve on timeout segmentation, as well as other previously published approaches, bringing the accuracy up to 92% for identifying fine-grained task boundaries, and 89-97% for identifying pairs of queries from the same task when tasks are interleaved hierarchically. This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. The ability to perform this kind of segmentation paves the way for evaluating search engines in terms of user task completion.", "proceedingsTitle": "Proceeding of the 17th ACM conference on Information and knowledge management", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "699–708", "series": "CIKM '08", "seriesNumber": "", "DOI": "10.1145/1458082.1458176", "ISBN": "978-1-59593-991-3", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "Napa Valley, California, USA", "shortTitle": "Beyond the session timeout", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "ACM ID: 1458176", "tags": [ { "tag": "algorithms", "type": 1 }, { "tag": "experimentation", "type": 1 }, { "tag": "measurement", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2011-04-15T07:52:49Z", "dateModified": "2011-04-15T07:52:49Z" } } ]