Abstract: Techniques for enhancing usability and electronic resource efficiency using job relevance are disclosed herein. In some embodiments, a list of a predetermined number of top job openings for a member of the social networking system is generated. The list is communicated to a device of the user for presentation in a user interface on the device. The user interface allows the member to browse through and provide an indication of a lack of relevancy of each of the list of the predetermined number of top job openings to the member and an indication of a reason for the lack of relevancy. Based on the user providing the indication of the lack of relevancy and the reason, a modified relevancy assessment of each of the plurality of job openings is generated. The list of the predetermined number of top job openings for the member is regenerated and communicated to the device.

Abstract: In an example embodiment, a fast and space-efficient ranking mechanism is used for vertical searches. A precedence is assigned to a plurality of features based on the relative importance of those features to the provider of a vertical search engine. In an example embodiment, this relative importance may be explicitly indicated by the provider of the vertical search engine. A unique data structure may then be created that incorporates the precedence of each feature.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for providing profiles with limited permission level functionality in the network. In response to receiving a request to post the new employment listing, a collaboration system updates a permission list of the employment listing to provide a first user account with an administrator permission level in relation to the employment listing. The administrator permission level provides a first function and a second function in relation to the employment listing. The collaboration system receives a request to tag a second user account to the employment listing and updates the permission list to provide the second user account with a limited permission level in relation to the employment listing. The limited permission level provides the second user account with permission to perform the first function in relation to the employment listing but does not provide permission to perform the second function.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for identifying profiles in a network based on relevance scores. A relevancy system identifies a set of candidate user profiles based on user profiles that correspond to users that are members of a first organization. For each candidate user profile, the relevancy system determines scores indicating a relevance level of the respective candidate user profile to an employment listing based on multiple relevance categories. The relevancy system applies weights to the scores and determined a relevance score for the candidate user profile based on the weighted relevancy scores. The weighs are determined based on historical hiring data and indicate a relative impact of each relevance category on hiring. The relevancy system selects a subset of the candidate user profiles based on the relevance scores and transmits notifications regarding the employment listing to the subset of the candidate user profiles.

Abstract: Techniques for assisting a user in conducting a search for online content are described. According to various embodiments, a set of search results is generated, in response to a user search query. A list of candidate facet-value pairs, for inclusion in a suggestion facet user interface element for display in-line with the set of search results, is then accessed. The suggestion facet user interface element may be configured, upon user selection, to filter the set of search results based on the corresponding facet-value pair. Thereafter, win rate information identifying win rates associated with each of the candidate facet-value pairs is accessed. A specific one of the candidate facet-value pairs having the highest win rate is then selected for inclusion in the suggestion facet user interface element.

Abstract: In an example embodiment, a fast and space-efficient ranking mechanism is used for vertical searches. A precedence is assigned to a plurality of features based on the relative importance of those features to the provider of a vertical search engine. In an example embodiment, this relative importance may be explicitly indicated by the provider of the vertical search engine. A unique data structure may then be created that incorporates the precedence of each feature.

Abstract: Techniques for enhancing usability and electronic resource efficiency using job relevance are disclosed herein. In some embodiments, a list of a predetermined number of top job openings for a member of the social networking system is generated. The list is communicated to a device of the user for presentation in a user interface on the device. The user interface allows the member to browse through and provide an indication of a lack of relevancy of each of the list of the predetermined number of top job openings to the member and an indication of a reason for the lack of relevancy. Based on the user providing the indication of the lack of relevancy and the reason, a modified relevancy assessment of each of the plurality of job openings is generated. The list of the predetermined number of top job openings for the member is regenerated and communicated to the device.

Abstract: Techniques for enhancing usability and electronic resource efficiency using job relevance are disclosed herein. In some embodiments, a plurality of members of the social networking system are identified for which the new job is relevant. The job posting is identified as a top job posting for each of a subset of the plurality of members for which the new job is relevant, the identifying of the job posting as a top job posting including accessing an online data store that includes enhanced relevancy data, the enhanced relevancy data including real-time feedback provided by one or more of the plurality of members with respect to the values of the attributes specified within the job posting. A specialized notification of the top job posting is generated for each of the identified subset of the identified plurality of members.

Abstract: Techniques for assisting a user in conducting a search for online content are described. According to various embodiments, a set of search results is generated, in response to a user search query. A list of candidate facet-value pairs, for inclusion in a suggestion facet user interface element for display in-line with the set of search results, is then accessed. The suggestion facet user interface element may be configured, upon user selection, to filter the set of search results based on the corresponding facet-value pair. Thereafter, win rate information identifying win rates associated with each of the candidate facet-value pairs is accessed. A specific one of the candidate facet-value pairs having the highest win rate is then selected for inclusion in the suggestion facet user interface element.

Abstract: Techniques for assisting a user in conducting an online job search for online job listings are described. According to various embodiments, a user specification of a job search query including at least one user-specified job search query term is received. Values for one or more member profile attributes of the user are then accessed. Thereafter, the job search query is modified based on the accessed values for the member profile attributes of the user, the modifying comprising inserting job search query terms corresponding to the values for the member profile attributes into the job search query. Search results corresponding to job listings posted on the job search engine are then generated, based on the modified job search query. Further, one or more of the search results may be displayed, via a user interface.

Abstract: Systems, methods and a machine-readable media are described herein for a relevance booster module to calculate a relevance, with respect to at least one characteristic of a query, of each piece of content in a set of collected content and a set of premium content. The relevance booster module increases a calculated relevance of at least one piece of content in the set of premium content. The relevance booster module generates a list in which each piece of content in the set of collected content and the set of premium content is ranked according to a respective calculated relevance.

Abstract: This patent application pertains to answer model comparison. One implementation can determine a first frequency at which an individual answer category appears in an individual slot on a query results page when utilizing a first model. The method can ascertain a second frequency at which the individual answer category appears in the individual slot on the query results page when utilizing a second model. The method can calibrate the second model so that the second frequency approaches the first frequency.

Abstract: Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.

Abstract: This patent application pertains to answer model comparison. One implementation can determine a first frequency at which an individual answer category appears in an individual slot on a query results page when utilizing a first model. The method can ascertain a second frequency at which the individual answer category appears in the individual slot on the query results page when utilizing a second model. The method can calibrate the second model so that the second frequency approaches the first frequency.

Abstract: Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.