Ian McCarthy

The disclosed systems and methods provide a technical solution to existing technical problems, especially those highlighted above, by providing an improved message partitioning and extraction framework that can be applied online, in real-time, at scale, without any pre-processing or pre-learning/training. The disclosed framework, according to some embodiments, partitions identified, received or incoming HTML content in email messages based on the relative positions of the links in the message's… Show more

The disclosed systems and methods provide a technical solution to existing technical problems, especially those highlighted above, by providing an improved message partitioning and extraction framework that can be applied online, in real-time, at scale, without any pre-processing or pre-learning/training. The disclosed framework, according to some embodiments, partitions identified, received or incoming HTML content in email messages based on the relative positions of the links in the message's DOM hierarchy. The partitioning is leveraged into identifying meaningful entities within the messages. For example, if a message constitutes a travel reservation, the resulting partition of the message will entail the identification of the travel information (e.g., travel dates, modes of transportation, traveler information, and the like) from the specific fields of the message. According to embodiments of the disclosed systems and methods, the effectiveness of the disclosed framework is in the detection or identification of the pertinent sections in these automatically generated email messages.

The technical steps performed by the disclosed framework are critical for many applications such as ad retargeting, mail search, and mail summarization, and can be leveraged to enhance many user-facing features, such as coupon clipping and travel alerts. As opposed to the approaches of conventional techniques, the disclosed framework embodies a novel, technically efficient approach that leverages the analysis of HTML links within messages, as they play a key role in identifying and extracting valuable information about an email message. Thus, the disclosed systems and methods are capable of automatically detecting key fragments in email messages by focusing solely on the links and their locations in the content. Show less

In accordance with the present disclosure, one or more computing devices and/or methods are provided. In an example, a plurality of email messages stored in a mailbox of a first email account of a first user may be identified. The plurality of email messages may be evaluated to identify a plurality of coupons in the mailbox. The plurality of coupons may be analyzed to determine one or more coupon features associated with the plurality of coupons. User data associated with the first user and… Show more

In accordance with the present disclosure, one or more computing devices and/or methods are provided. In an example, a plurality of email messages stored in a mailbox of a first email account of a first user may be identified. The plurality of email messages may be evaluated to identify a plurality of coupons in the mailbox. The plurality of coupons may be analyzed to determine one or more coupon features associated with the plurality of coupons. User data associated with the first user and activity data associated with the first user may be analyzed to determine one or more user features associated with the first user. A predictive model for the first email account may be tuned based upon the one or more coupon features and the one or more user features. A set of scores may be generated for the plurality of coupons based upon the predictive model, wherein the set of scores comprises a score for each coupon of the plurality of coupons. A graphical user interface of a first client device may be controlled, based upon the set of scores of the plurality of coupons, to display one or more coupons of the plurality of coupons via an interface associated with the first email account. Show less

In a method of ranking or filtering new content items for presentation to members of a group of users of a social-networking service, content items that are candidates for presentation to the members are received. A user of the social-networking service is enabled to serve as a curator of the candidates, with the enabling including enabling the user to scroll through subsets of the candidates in a carousel user interface to indicate an opinion of the user with respect to an importance to the… Show more

In a method of ranking or filtering new content items for presentation to members of a group of users of a social-networking service, content items that are candidates for presentation to the members are received. A user of the social-networking service is enabled to serve as a curator of the candidates, with the enabling including enabling the user to scroll through subsets of the candidates in a carousel user interface to indicate an opinion of the user with respect to an importance to the group of each of one or more candidates. One or more of the candidates are presented to the members of the group based on the opinion of the user with respect to the candidates. Show less

The present disclosure relates to methods and systems for clustering individual items of web content, and then utilizing activity and profile data to both select clusters of content items for presentation to a user, and determining how the selected clusters of content items are presented to the user of an online social network service. With some embodiments, the activity data are derived by monitoring and detection interactions with the individual items of web content by an individual user, or… Show more

The present disclosure relates to methods and systems for clustering individual items of web content, and then utilizing activity and profile data to both select clusters of content items for presentation to a user, and determining how the selected clusters of content items are presented to the user of an online social network service. With some embodiments, the activity data are derived by monitoring and detection interactions with the individual items of web content by an individual user, or other users with whom the individual user is related, as established via, and defined by, the social network service. Show less

The present teaching relates to providing a recommendation for subscribing to or unsubscribing from an electronic communication. In one example, actions of a user are obtained with respect to electronic communications of the user. One or more categories of the electronic communications are determined. A state of the user is determined based on the actions and the one or more categories. The state is either a discovery state indicating that the user expresses an interest to receive electronic… Show more

The present teaching relates to providing a recommendation for subscribing to or unsubscribing from an electronic communication. In one example, actions of a user are obtained with respect to electronic communications of the user. One or more categories of the electronic communications are determined. A state of the user is determined based on the actions and the one or more categories. The state is either a discovery state indicating that the user expresses an interest to receive electronic communications associated with a specific category or a cleaning state indicating that the user lacks an interest in one or more received electronic communications. A subscribe recommendation for subscribing to electronic communications associated with the specific category is provided when the state is determined to be a discovery state. An unsubscribe recommendation for unsubscribing from electronic communications similar to the one or more received electronic communications is provided when the state is determined to be a cleaning state.
Show less

"The disclosed embodiments relate to digest emails for groups.
More specifically, the disclosed embodiments relate to techniques for increasing
the relevance of the digest emails to members of the groups......"

In a method of ranking or filtering new content items for presentation to members of a group of users of a social-networking service, content items that are candidates for presentation to the members are received. A user of the social-networking service is enabled to serve as a curator of the candidates, with the enabling including enabling the user to scroll through subsets of the candidates in a carousel user interface to indicate an opinion of the user with respect to an importance to the… Show more

In a method of ranking or filtering new content items for presentation to members of a group of users of a social-networking service, content items that are candidates for presentation to the members are received. A user of the social-networking service is enabled to serve as a curator of the candidates, with the enabling including enabling the user to scroll through subsets of the candidates in a carousel user interface to indicate an opinion of the user with respect to an importance to the group of each of one or more candidates. One or more of the candidates are presented to the members of the group based on the opinion of the user with respect to the candidates. Show less