Abstract: The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

Abstract: The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

Abstract: The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

Abstract: The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

Abstract: The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing location queries. In one aspect, a method includes obtaining a location search profile for a user. The location search profile specifies, for each geographic location, a set of references to location resources that were previously requested through user interaction, by the user, with previous search results that were provided in response to a previous location query. A current location query is received from a user device that is associated with the user. In response to receiving the current location query a reference to at least one of the location resources from the set of references and search results responsive to the current location query are selected. In turn, data that cause presentation of the selected reference and the search results are provided.

Abstract: A computer-implemented information targeting method is disclosed. The method includes receiving a search query from a computing device, where the search query has at least two different meanings, identifying metadata associated with the search query, using the metadata to promote search results corresponding to a first meaning of the at least two meanings of the search query, and providing search results corresponding to the first meaning of the search query to the computing device. Using the metadata to promote search results may comprise analyzing (a) prior search queries that are related to the received search query, (b) metadata associated with the prior search queries, and (c) selections of search results provided in response to the prior search queries; and identifying a correlation between the metadata associated with the prior search queries and selections of search results presented in response to the prior search queries.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing location queries. In one aspect, a method includes obtaining a location search profile for a user. The location search profile specifies, for each geographic location, a set of references to location resources that were previously requested through user interaction, by the user, with previous search results that were provided in response to a previous location query. A current location query is received from a user device that is associated with the user. In response to receiving the current location query a reference to at least one of the location resources from the set of references and search results responsive to the current location query are selected. In turn, data that cause presentation of the selected reference and the search results are provided.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting content items for presentation. In one aspect, a method includes receiving a content item request that references a geographic location. A set of targeted phrases for the geographic location are received. The set of targeted phrases specify one or more targeted phrases that are each specified as a targeting criterion for at least a threshold number of content items for which a reference to the geographic location is also specified as a targeting criterion. A set of targeted queries for the geographic location are selected. Eligible content items are selected based on the set of targeted queries. In turn, data that cause presentation of at least one of the eligible content items are provided.

Abstract: An ad-selection analysis subsystem (“analysis subsystem”) analyzes advertisement selection data to identify relevant queries for advertisements. Advertisement selection data for each advertisement in a set of advertisements are represented as a vector of terms corresponding to search queries for which the corresponding advertisement was provided with search results and, in turn, selected by a user. A clustering algorithm is applied to the advertisement selection data for the set of advertisements to identify clusters of search queries and corresponding clusters of advertisements. Identified clusters can be used, for example, to facilitate query expansion, advertisement selection, and keyword generation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating and applying query rules. Search queries that are received during user sessions are analyzed to generate query rules that specify a high-performing query that can be used to identify content in response to receipt of a low-performing query. The query rules can be generated by identifying queries that are received in a same user sub-session and defining initial query pairs that each have a high-performing query and a low-performing query from the same user sub-session. The initial query pairs that are identified in a threshold number of user sub-sessions are classified as reference query pairs with which query rules are defined. Query rules are made available to a search system, advertisement management system, or another query processing system for identifying content responsive to search queries.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for search labels. In one aspect, a method includes receiving an association by a first user of a first label to a first search result in a plurality of first search results that were provided to the first user in response to a query submitted by the first user, and wherein a second user is unable to view the association. Permission is granted on behalf of the first user to allow the second user to share the first label. And, subsequent to granting permission, an association of the first label by the second user to a third search result in a plurality of third search results that were provided to the second user in response to a query submitted by the second user is received.