Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a feature set for a model to be trained by machine learning. A subset of features from the feature set can be associated with entities having relationship types and corresponding to pages on a social networking system. The feature set can be reduced based on at least one rule applied to the relationship types.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: Some embodiments include a method of detecting memes, as “key terms,” in a chatter aggregation in a social networking system. The method can include aggregating user-generated content objects within the social networking system into the chatter aggregation according to a set of filters. A meme analysis engine can define a target group within the chatter aggregation to compare against a background group. The meme analysis engine can extract key terms from textual content of the target group. The meme analysis engine can determine a relevancy rank of a term in the key terms based on an accounting of the term in the textual content of the target group and a linguistic relevance score of the term according to a linguistic model.

Abstract: Some embodiments include a stream consolidation engine in a social networking system. The stream consolidation engine can receive two or more input data streams (e.g., an activity record data stream and an application service output stream) from the social networking system. The stream consolidation engine can merge an activity record from the activity record data stream with at least a data record from the input data streams (e.g., from the activity record data stream or the application service output stream) to create a conglomerate data record. The stream consolidation engine can supplement the conglomerate data record with asynchronous information from a data storage or derivative data computed based on content in or referenced by the conglomerate data record. The stream consolidation engine can publish the conglomerate data record in a consolidated data stream. The consolidated data stream can be substantially synchronous to at least one of the input data streams.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a first score generated by a first scoring algorithm that determines a degree to which a resume is matched to a job pipeline of an organization. A second score generated by a second scoring algorithm that determines a degree to which the resume is matched to the job pipeline is determined. The first score and the second score are processed to generate an aggregate score.

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine scores regarding suitability of connections of a user for employment with an organization with which the user is employed based on a first machine learning model. Job titles for which the connections are suited are determined based on a second machine learning model. A user interface for presenting in real time information relating to the connections and associated job titles determined for the connections is generated.

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a feature set for a model to be trained by machine learning. A subset of features from the feature set can be associated with entities having relationship types and corresponding to pages on a social networking system. The feature set can be reduced based on at least one rule applied to the relationship types.

Abstract: Some embodiments include a stream consolidation engine in a social networking system. The stream consolidation engine can receive two or more input data streams (e.g., an activity record data stream and an application service output stream) from the social networking system. The stream consolidation engine can merge an activity record from the activity record data stream with at least a data record from the input data streams (e.g., from the activity record data stream or the application service output stream) to create a conglomerate data record. The stream consolidation engine can supplement the conglomerate data record with asynchronous information from a data storage or derivative data computed based on content in or referenced by the conglomerate data record. The stream consolidation engine can publish the conglomerate data record in a consolidated data stream. The consolidated data stream can be substantially synchronous to at least one of the input data streams.

Abstract: Some embodiments include a method of detecting memes, as “key terms,” in a chatter aggregation in a social networking system. The method can include aggregating user-generated content objects within the social networking system into the chatter aggregation according to a set of filters. A meme analysis engine can define a target group within the chatter aggregation to compare against a background group. The meme analysis engine can extract key terms from textual content of the target group. The meme analysis engine can determine a relevancy rank of a term in the key terms based on an accounting of the term in the textual content of the target group and a linguistic relevance score of the term according to a linguistic model.

Abstract: Some embodiments include a method of performing a content analysis study around a central theme utilizing a concept study system. The concept study system can generate a classifier machine corresponding to the content analysis study based on a super topic taxonomy including one or more concept identifiers. The concept study system can process a content object, associated with a user activity in a social networking system, through the classifier machine to determine whether to assign the user activity to the content analysis study. The concept study system can aggregate at least an attribute derived from the user activity in a study-specific data container associated with the content analysis study and compute a statistical or analytical insight based on aggregated attributes in the study-specific data container.

Abstract: A social networking system receives a selection of user characteristics defining a benchmark audience and a target audience, and generates audience metrics that compare the audiences across a set of user characteristics. These user characteristics include demographics, interests, purchasing activity, and actions on the social networking system. The audience metrics are provided to an advertiser who may select additional user characteristics to refine the benchmark or target audiences. The audience metrics may include an affinity score that compares the audience metrics for a particular type of interaction, and may normalize the frequency of interactions relative to interactions of the audience as a whole. Advertisers may use the defined audiences to establish targeting criteria for an advertisement, and may use existing targeting criteria to seed the selection of an audience.

Abstract: A social networking system receives a selection of user characteristics defining a benchmark audience and a target audience, and generates audience metrics that compare the audiences across a set of user characteristics. These user characteristics include demographics, interests, purchasing activity, and actions on the social networking system. The audience metrics are provided to an advertiser who may select additional user characteristics to refine the benchmark or target audiences. The audience metrics may include an affinity score that compares the audience metrics for a particular type of interaction, and may normalize the frequency of interactions relative to interactions of the audience as a whole. Advertisers may use the defined audiences to establish targeting criteria for an advertisement, and may use existing targeting criteria to seed the selection of an audience.

Abstract: A social networking system receives a selection of user characteristics defining a benchmark audience and a target audience, and generates audience metrics that compare the audiences across a set of user characteristics. These user characteristics include demographics, interests, purchasing activity, and actions on the social networking system. The audience metrics are provided to an advertiser who may select additional user characteristics to refine the benchmark or target audiences. The audience metrics may include an affinity score that compares the audience metrics for a particular type of interaction, and may normalize the frequency of interactions relative to interactions of the audience as a whole. Advertisers may use the defined audiences to establish targeting criteria for an advertisement, and may use existing targeting criteria to seed the selection of an audience.

Abstract: A social networking system infers a sentiment polarity of a user toward content of a page. The sentiment polarity of the user is inferred based on received information about an interaction between the user and the page (e.g., like, report, etc.), and may be based on analysis of a topic extracted from text on the page. The system infers a positive or negative sentiment polarity of the user toward the content of the page, and that sentiment polarity then may be associated with any second or subsequent interaction from the user related to the page content. The system may identify a set of trusted users with strong sentiment polarities toward the content of a page or topic, and may use the trusted user data as training data for a machine learning model, which can be used to more accurately infer sentiment polarity of users as new data is received.