Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: An online system predicts topics for content items. The online system provides one or more topic labels for a user to apply concurrently while a user is composing a post, in response to requests periodically received from the user's device. A request includes information such as content composed by the user and contextual information. The online system employs machine learning techniques to analyze content composed by a user and contextual information thereby to predict topic labels. Different machine learning models for classifying individual topic labels, identifying relevant topic labels, and/or detecting changes in existing topic predictions are developed. Some machine learning models predict topics for full content and some predict topics for partial content. The online system trains the machine learning models to ensure accurate topic predictions are provided timely. The online system employs various machine learning model training methods such as active training and gradient training.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: An online system predicts topics for content items. The online system provides one or more topic labels for a user to apply concurrently while a user is composing a post, in response to requests periodically received from the user's device. A request includes information such as content composed by the user and contextual information. The online system employs machine learning techniques to analyze content composed by a user and contextual information thereby to predict topic labels. Different machine learning models for classifying individual topic labels, identifying relevant topic labels, and/or detecting changes in existing topic predictions are developed. Some machine learning models predict topics for full content and some predict topics for partial content. The online system trains the machine learning models to ensure accurate topic predictions are provided timely. The online system employs various machine learning model training methods such as active training and gradient training.

Abstract: An online system, such as a social networking system, displays a plurality of advertisements to users. The system selects an ad to display to a user based on a bidding system. The system receives feedback and user engagement data for an ad to compare the ad to other ads that are targeted to a similar group of users, to generate a relevance score. The relevance score can be provided to an advertiser as a way to quantify the effectiveness of the ad, and it reflects user engagement with the advertisement. In some embodiments, a projected relevance score can be calculated for a prospective advertisement by analyzing the content of the prospective ad prior to receiving user engagement data by comparing the prospective advertisement's content to other ads for which user engagement data does exist.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

Abstract: A social networking system modifies a bid amount associated with advertisements in an advertising campaign based on a target average price paid associated with the advertising campaign. A bid amount is determined from the target average price paid and associated with advertisements from the advertising campaigns in various advertisement selection processes. From advertisement selection processes in which an advertisement from the advertising campaign was selected, an average amount charged to the advertiser is determined. Based on the target average price paid and the average amount charged to the advertiser, the bid amount is modified. In subsequent advertisement selection processes, the modified bid amount is associated with advertisements from the advertising campaign.