Facebook, Inc.

Yahoo! Inc.

Yun-Fang Juan

Mark E Zuckerberg

Andrew Garrod Bosworth

Adam Edward D'Angelo

Justin M Rosenstein

Chamath M Palihapitiya

Timothy A Kendall

Yishan Wong

Matthew R Cohler

Robert Kang-Xing Jin

Kang-Xing Jin

Adam D'angelo

Amr Awadallah

Chi-Chao Chang

Ming Hua

Robert Kang Xing Jin

Aditya Agarwal

Levy Klots

Oleksandr Moskalyuk

A social networking system generates socially-relevant stories for a user based on actions taken by other users to whom the user is connected. The social networking system may receive a request for a sponsored story for a viewing user and may select information about one or more actions performed by one or more users to whom the viewing user is connected to identify one of a plurality of candidate information for a sponsored story based on one or more criteria (e.g., affinity of the viewing user for the candidates, expected value for the candidates, etc.). The social networking system may also generate the sponsored story and generate a feed comprising the sponsored story and news stories (e.g., non-sponsored stories) about one or more users of the social networking system with whom the viewing user is connected. This feed may be provided for display to the viewing user.

Social advertisements and other informational messages on a social networking website, and advertising model for same

A user's connections in a social networking system are grouped into a number of clusters based on a measure of the connections' relationships, or affinity, to each other. The affinities among the connections are based on the connections' own relationships and indicate a likelihood that the connections are in the same social circles. The clusters are formed based on the affinities among the user's connections, where the clusters tend to have connections that have relatively high affinities with the other connections the same cluster as compared to the connections who are not in the same cluster. An iterative hierarchical clustering algorithm may be used to collapse the connections into clusters based on affinities between pairs of the connections.

Clustering a user's connections in a social networking system

A social networking system selects a subset of keywords from a set of master keywords found in user profiles. The method includes selecting a first and second group of user profiles including one or more keywords and computing the number of occurrences of each of the master keywords in the first and second group of profiles. A value may be computed for each of the master keywords based on a comparison of the number of occurrences in the first group of profiles and the number of occurrences in the second group of profiles. The computed value may be used for selecting the subset of keywords from the master keywords and/or ranking the master keywords.

Prediction of user response to invitations in a social networking system based on keywords in the user's profile

Prediction of user response to invitations in a social network system based on keywords in the user's profile

A social networking system generates socially-relevant ads for a user based on actions taken by other users to whom the user is connected. These may be actions taken on, and determined by, an external system, information about which actions can be received by the social networking system and used for matching to an advertisement request. The social networking system may determine a social context for advertising to a user based on the action and may generate an advertisement for the matched ad request that includes an informational message communicating the social context (i.e., an ad with the information message appended to it, a news story for the informational message, etc.). The ad may be targeted to the user based on user affinity for the ad, based on an object interacted with or an action taken by the user's connections on or external to the social networking system, among other criteria.

Social advertisements based on actions on an external system

A social networking system generates socially-relevant stories for a user based on other users (e.g., based on actions taken by other users) to whom the user is connected. These socially-relevant stories, including news stories, social advertisements, etc., may be presented on a web page within a domain of an external system that is different from the domain of the social networking system. When a web page from an external system is requested for a viewing user, the social content about other users who are connected to the viewing user may be provided by the social networking system for that viewing user. This personalized social content may be presented in a frame (e.g., an iframe) of the external web page rendered and provided for display to the viewing user.

Presenting personalized social content on a web page of an external system

In accordance with aspects disclosed herein, impact that a user interface design has on a user's experience is measured. User response to one or more user interface designs is measured. Two or more user interface designs can be compared based on user response to each design. A single user interface design can be evaluated based on one or more measures of user response to the user interface, or two or more user interface designs can be compared using one or more user response measures corresponding to the user interface designs.

System and method of identifying and measuring response to user interface design

Predicting user responses to invitations in a social networking system based on keywords in user profiles

A system and method for selecting a subset of keywords from a set of master keywords found in user profiles in a social network is disclosed. The method includes selecting a first and second group of user profiles including one or more keywords and computing the number of occurrences of each of the master keywords in the first and second group of profiles. A value may be computed for each of the master keywords based on a comparison of the number of occurrences in the first group of profiles and the number of occurrences in the second group of profiles. The computed value may be used for selecting the subset of keywords from the master keywords and/or ranking the master keywords.

Systems and methods for observing responses to invitations by users in a web-based social network

Growing community of inventors

San Jose, CA, United States of America

Yun-Fang Juan