Abstract: An online system may identify content with which a user has an interest. For example, the online system may determine that a user has an interest in the content based on interaction information indicating that the user interacted with the content. In a particular example, the online system may identify image concepts included in the content based on computer vision techniques that recognize the image concepts. The online system may model probabilities that image concepts will appeal to users. Based on the modeled probabilities, the online system may automatically recommend image concepts for inclusion in candidate images, automatically generate candidate images, or assess candidate images to determine a probability of user interaction with the assessed candidate images.

Abstract: An online system may identify content with which a user has an interest. For example, the online system may determine that a user has an interest in the content based on interaction information indicating that the user interacted with the content. In a particular example, the online system may identify image concepts included in the content based on computer vision techniques that recognize the image concepts. The online system may model probabilities that image concepts will appeal to users. Based on the modeled probabilities, the online system may automatically recommend image concepts for inclusion in candidate images, automatically generate candidate images, or assess candidate images to determine a probability of user interaction with the assessed candidate images.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a workflow configuration including a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. The DG can be executed by various types of computation platforms. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the workflow configuration.

Abstract: Techniques for identifying mutual interests between users of a social networking system are disclosed herein. In one embodiment, a method includes steps of identifying, in a social networking system, a content object that has been interacted by a first user of the social networking system; associating, in the social networking system, a keyword with the first user, the keyword having been previously associated with the content object; and determining, in the social networking system, a mutual interest for the first user and a second user of the social networking system by identifying a match between the keyword associated with the first user with a keyword associated with the second user.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a workflow configuration including a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. The DG can be executed by various types of computation platforms. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the workflow configuration.

Abstract: An online system classifies users based on their propensity to adopt one or more innovations in a subject area. To classify the users, the online system maintains information associated with one or more actions performed by the user and content provided by the user, with actions and the content associated with adopting one or more innovations in the subject area. The online system determines a score for a pairing of the user and the subject area based on the maintained one or more actions and/or the content associated with adopting the one or more innovations in the subject area. Based on the determined score, the online system determines an innovation adoption label for the user that represents a propensity of the user to adopt one or more innovations in the subject area.

Abstract: Techniques for compressing images based on context are provided. A first image and a second image may be identified for display on a client device. One or more contexts of the first image may be identified. One or more contexts of the second image may be identified. A first image quality for the first image may be determined based on the one or more contexts of the first image. A second image quality for the second image may be determined based on the one or more contexts of the second image. The first image may be compressed at the first image quality and the second image at the second image quality. The compressed first image and the compressed second image may be transmitted to the client device.

Abstract: In one embodiment, a method includes defining an input data space, defining a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow, wherein at least one of the plurality of transformation blocks includes logic to dynamically modify the DG during execution of the experiment workflow, formatting the DG and the input data space into a data structure such that the data structure is interpretable by a plurality of different computation platforms, scheduling a distributed computation platform selected from the plurality of different computation platforms to execute the experiment workflow according to the input data space and the DG, and imperatively programming computing nodes of the distributed computation platform to execute the experiment workflow based on the DG if at least one of the transformation blocks dynamically modifies the DG during the execution of the experiment workflow.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a workflow configuration including a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. The DG can be defined graphically. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the workflow configuration.

Abstract: Techniques for identifying mutual interests between users of a social networking system are disclosed herein. In one embodiment, a method includes steps of identifying, in a social networking system, a content object that has been interacted by a first user of the social networking system; associating, in the social networking system, a keyword with the first user, the keyword having been previously associated with the content object; and determining, in the social networking system, a mutual interest for the first user and a second user of the social networking system by identifying a match between the keyword associated with the first user with a keyword associated with the second user.

Abstract: Techniques for identifying mutual interests between users of a social networking system are disclosed herein. In one embodiment, a method includes steps of identifying, in a social networking system, a content object that has been interacted by a first user of the social networking system; associating, in the social networking system, a keyword with the first user, the keyword having been previously associated with the content object; and determining, in the social networking system, a mutual interest for the first user and a second user of the social networking system by identifying a match between the keyword associated with the first user with a keyword associated with the second user.

Abstract: In one embodiment, dividing a set of texts into one or more text blocks, each text block including a portion of the set of texts; rendering each text block to obtain one or more rendered text blocks; determining a placement instruction for each rendered text block, the placement instruction indicating a position of the rendered text block when it is displayed; and sending the one or more rendered text blocks and their respectively associated placement instructions to an electronic device for displaying on the electronic device.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. At least one of the transformation block can dynamically modify the DG. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the DG.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a workflow configuration including a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. The DG can be executed by various types of computation platforms. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the workflow configuration.

Abstract: Various embodiments include a classification platform system. A user can define a classification experiment on the classification platform system. For example, the user can define an input data space by selecting at least one of data sources interfaced with the classification platform system and defining a workflow configuration including a directed graph (DG) connecting a plurality of transformation blocks to represent an experiment workflow. The DG can specify how one or more outputs of each of the transformation blocks are fed into one or more other transformation blocks. The DG can be defined graphically. The classification platform system can schedule the experiment workflow to be executed on a distributed computation platform according to the input data space and the workflow configuration.

Abstract: Techniques for emotion detection and content delivery are described. In one embodiment, for example, an emotion detection component may identify at least one type of emotion associated with at least one detected emotion characteristic. A storage component may store the identified emotion type. An application programming interface (API) component may receive a request from one or more applications for emotion type and, in response to the request, return the identified emotion type. The one or more applications may identify content for display based upon the identified emotion type. The identification of content for display by the one or more applications based upon the identified emotion type may include searching among a plurality of content items, each content item being associated with one or more emotion type. Other embodiments are described and claimed.

Abstract: An apparatus to identify and purge unused code may comprise a processor circuit on a device and a storage component configured to store a codebase including one or more portions of programming code. The apparatus may further comprise a sampling component, a profiling component, and a purge component. The sampling component may sample the codebase and generate one or more leads identifying portions of programming code from the codebase determined to be unused during a sampling period. The profiling component may receive the one or more leads and profile programming code identified therein during a profiling period and to identify portions of programming code determined to be unused during the profiling period. The purge component may receive identification of the portions of programming code determined to be unused during the profiling period and initiate a purging process thereon. Other embodiments are described and claimed.

Abstract: Techniques for emotion detection and content delivery are described. In one embodiment, for example, an emotion detection component may identify at least one type of emotion associated with at least one detected emotion characteristic. A storage component may store the identified emotion type. An application programming interface (API) component may receive a request from one or more applications for emotion type and, in response to the request, return the identified emotion type. The one or more applications may identify content for display based upon the identified emotion type. The identification of content for display by the one or more applications based upon the identified emotion type may include searching among a plurality of content items, each content item being associated with one or more emotion type. Other embodiments are described and claimed.

Abstract: An online system classifies users based on their propensity to adopt one or more innovations in a subject area. To classify the users, the online system maintains information associated with one or more actions performed by the user and content provided by the user, with actions and the content associated with adopting one or more innovations in the subject area. The online system determines a score for a pairing of the user and the subject area based on the maintained one or more actions and/or the content associated with adopting the one or more innovations in the subject area. Based on the determined score, the online system determines an innovation adoption label for the user that represents a propensity of the user to adopt one or more innovations in the subject area.

Abstract: Techniques for compressing images based on context are provided. A first image and a second image may be identified for display on a client device. One or more contexts of the first image may be identified. One or more contexts of the second image may be identified. A first image quality for the first image may be determined based on the one or more contexts of the first image. A second image quality for the second image may be determined based on the one or more contexts of the second image. The first image may be compressed at the first image quality and the second image at the second image quality. The compressed first image and the compressed second image may be transmitted to the client device.