Abstract: An online system selects for display content items having an option to allow a user to converse with a content provider over an electronic communication system in a way that optimizes for the occurrence of that communication. Content items provided by the online system include links to an online communication system from which the online system can directly observe whether the user engaged in communications with third parties. The online system can thus obtain labeled training data describing communications between users and users' previous interactions with content items and pages of the online system. The trained model is applied to candidate content items to predict a probability that a user will engage in a communication with the content provider if the content is provided to the user, and the model optimizes the selection of content items for which the call to action is to engage in the communication.

Abstract: A user trainable user interface page classification system applies a rule set to information associated with a user interface page to determine whether the user interface page satisfies a domain page condition. If the user interface page does not satisfy the domain page condition, a user trains the system such that the user interface page classification system classifies the user interface page as a domain page. The rule set of the user interface page classification system is updated, and the updated rule set is applied to the information associated with the user interface page. The user interface page classification system then classifies the user interface page as a domain page.

Abstract: An online system selects for display content items having an option to allow a user to converse with a content provider over an electronic communication system in a way that optimizes for the occurrence of that communication. Content items provided by the online system include links to an online communication system from which the online system can directly observe whether the user engaged in communications with third parties. The online system can thus obtain labeled training data describing communications between users and users' previous interactions with content items and pages of the online system. The trained model is applied to candidate content items to predict a probability that a user will engage in a communication with the content provider if the content is provided to the user, and the model optimizes the selection of content items for which the call to action is to engage in the communication.

Abstract: A user trainable user interface page classification system applies a rule set to information associated with a user interface page to determine whether the user interface page satisfies a domain page condition. If the user interface page does not satisfy the domain page condition, a user trains the system such that the user interface page classification system classifies the user interface page as a domain page. The rule set of the user interface page classification system is updated, and the updated rule set is applied to the information associated with the user interface page. The user interface page classification system then classifies the user interface page as a domain page.

Abstract: Representative embodiments disclose a browser plug-in designed to conserve bandwidth, power or computing resources. The plug-in identifies links in a web page that retrieve additional data. In some embodiments, the additional data is retrieved and examined to obtain an identifier associated with the data. The identifier is then used to determine a course of action which could be to block the data, move the data or ask that future data comply with the interests of the user. The web page is rendered and displayed in accordance with the decision. In other embodiments, prior to receiving data, the browser plug-in sends information to identify data of interest or disinterest and in response, receives data chosen based on the interest or disinterest, thus refraining from downloading irrelevant data. In still other embodiments, prior to receiving the data, the browser plug-in sends information indicating the data will not be retrieved.

Abstract: The present disclosure is directed toward systems, methods, and computer-readable media that automatically detect and correct advertising exploits for an advertising campaign. For instance, one or more of the systems disclosed herein employs various metrics to automatically determine when an advertising campaign exceeds an exploit threshold. In addition, upon determining that an advertising campaign is an exploit campaign, one or more of the disclosed systems automatically throttles the execution of an advertising campaign until the exploit is corrected. For example, the disclosed system can modify one or more of the campaign parameters of the exploit campaign to limit placement of at least one future advertisement from the advertising campaign.

Abstract: Representative embodiments disclose a browser plug-in designed to conserve bandwidth, power or computing resources. The plug-in identifies links in a web page that retrieve additional data. In some embodiments, the additional data is retrieved and examined to obtain an identifier associated with the data. The identifier is then used to determine a course of action which could be to block the data, move the data or ask that future data comply with the interests of the user. The web page is rendered and displayed in accordance with the decision. In other embodiments, prior to receiving data, the browser plug-in sends information to identify data of interest or disinterest and in response, receives data chosen based on the interest or disinterest, thus refraining from downloading irrelevant data. In still other embodiments, prior to receiving the data, the browser plug-in sends information indicating the data will not be retrieved.

Abstract: Representative embodiments disclose a browser plug-in designed to conserve bandwidth, power or computing resources. The plug-in identifies links in a web page that retrieve additional data. In some embodiments, the additional data is retrieved and examined to obtain an identifier associated with the data. The identifier is then used to determine a course of action which could be to block the data, move the data or ask that future data comply with the interests of the user. The web page is rendered and displayed in accordance with the decision. In other embodiments, prior to receiving data, the browser plug-in sends information to identify data of interest or disinterest and in response, receives data chosen based on the interest or disinterest, thus refraining from downloading irrelevant data. In still other embodiments, prior to receiving the data, the browser plug-in sends information indicating the data will not be retrieved.

Abstract: A user trainable user interface page classification system applies a rule set to information associated with a user interface page to determine whether the user interface page satisfies a domain page condition. If the user interface page does not satisfy the domain page condition, a user trains the system such that the user interface page classification system classifies the user interface page as a domain page. The rule set of the user interface page classification system is updated, and the updated rule set is applied to the information associated with the user interface page. The user interface page classification system then classifies the user interface page as a domain page.

Abstract: Representative embodiments disclose a browser plug-in designed to conserve bandwidth, power or computing resources. The plug-in identifies links in a web page that retrieve additional data. In some embodiments, the additional data is retrieved and examined to obtain an identifier associated with the data. The identifier is then used to determine a course of action which could be to block the data, move the data or ask that future data comply with the interests of the user. The web page is rendered and displayed in accordance with the decision. In other embodiments, prior to receiving data, the browser plug-in sends information to identify data of interest or disinterest and in response, receives data chosen based on the interest or disinterest, thus refraining from downloading irrelevant data. In still other embodiments, prior to receiving the data, the browser plug-in sends information indicating the data will not be retrieved.