A cyber-threat defense system for a network including its email domain protects this network from cyber threats. Modules utilize machine learning models as well communicate with a cyber threat module. Modules analyze the wide range of metadata from the observed email communications. The cyber threat module analyzes with the machine learning models trained on a normal behavior of email activity and user activity associated with the network and in its email domain in order to determine when a deviation from the normal behavior of email activity and user activity is occurring. A mass email association detector determines a similarity between highly similar emails being i) sent from or ii) received by a collection of two or more individual users in the email domain in a substantially simultaneous time frame. Mathematical models can be used to determine similarity weighing in order to derive a similarity score between compared emails.

A system for delivering notification messages across different notification media comprises a processor. A processor is configured to provide an indication of a new platform notification channel to one or more platform notification services. The indication is provided to one of the one or more platform notification services through a communication module specific to the one of the one or more platform notification services. The processor is configured to create a mapping from a new universal notification channel to a set of one or more platform notification channel identifiers. Each platform notification channel identifier of the set of platform notification channel identifiers is received from a platform notification service. The processor is configured to provide the set of one or more platform notification channel identifiers to a content provider of the new universal notification channel. The processor is coupled to the memory and is configured to store instructions.

A system for delivering notification messages across different notification media comprises a processor. A processor is configured to provide an indication of a new platform notification channel to one or more platform notification services. The indication is provided to one of the one or more platform notification services through a communication module specific to the one of the one or more platform notification services. The processor is configured to create a mapping from a new universal notification channel to a set of one or more platform notification channel identifiers. Each platform notification channel identifier of the set of platform notification channel identifiers is received from a platform notification service. The processor is configured to provide the set of one or more platform notification channel identifiers to a content provider of the new universal notification channel. The processor is coupled to the memory and is configured to store instructions.

The present disclosure relates to systems, methods, and computer-readable media for selectively analyzing content of electronic communications and enabling a sender to modify content to comply with one or more accessibility preferences. For example, systems disclosed herein may enable a client device to selectively analyze portions of an electronic communication and provide an accessibility alert indicator that one or more accessibility violations exist for a corresponding set of recipients. In addition, systems disclosed herein involve selectively applying a dynamic set of accessibility rules to content of the electronic document based on recipients that are added or removed as well as content of the electronic communication as it is composed.

The present disclosure relates to systems, methods, and computer-readable media for selectively analyzing content of electronic communications and enabling a sender to modify content to comply with one or more accessibility preferences. For example, systems disclosed herein may enable a client device to selectively analyze portions of an electronic communication and provide an accessibility alert indicator that one or more accessibility violations exist for a corresponding set of recipients. In addition, systems disclosed herein involve selectively applying a dynamic set of accessibility rules to content of the electronic document based on recipients that are added or removed as well as content of the electronic communication as it is composed.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sending a reduced size message. One of the methods includes receiving, by a wireless device, a request to send, over a wireless network, a message comprising one or more phrases; determining that a connection quality for the wireless network does not satisfy a connection quality threshold; generating, responsive to determining that the connection quality threshold is not satisfied, a reduced-size message based at least in part on the one or more phrases; and sending, by the wireless device and via the wireless network, the reduced-size message.

A message processing method performed by a computer system comprising at least one processor, the at least one processor being configured to execute computer-readable instructions included in a memory, the message processing method including recognizing, by the at least one processor, a language related to a conversation space based on a conversation context and a translation-related option to obtain a recognized language, the translation-related option being set for the conversation space, and providing, by the at least one processor, at least one translated text according to the recognized language for a message in the conversation space.

Embodiments include computer-implemented methods and systems for detecting undesirable and potentially harmful online behavior. The embodiments described and claimed could also be applied to detecting any other type of online behavior to be detected, but the descriptions focuses on detecting online violence. More particularly, the embodiments disclosed relate to detecting online violence using symbolic methods of natural language processing (NLP) that utilize and govern the usage of: 1) syntactic parser for analyzing grammatical context of the input text data, 2) unsupervised learning methods for improving selected aspects of the system and adjusting the system to new data sources and guidelines, and 3) statistical classifiers for resolving specific well-defined sub-tasks, in which statistical approaches surpass the symbolic methods.

Method of generating invitation media overlays for private collections starts with processor receiving first media content item from first client device associated with first user. Processor receives from first client device a selection of invitation media overlay to be applied to media content item. Invitation media overlay is associated with private collection of media content items. Processor generates modified first media content item by overlaying invitation media overlay on first media content item. Processor generates the private collection of media content items including modified first media content item. Processor receives from first client device selection of second user associated with the second user and causes modified first media content item to be displayed by the second client device. Processor receives selection of invitation media overlay from second client device and causes the private collection of media content items to be displayed by second client device. Other embodiments are described herein.

Systems and method for determining a topic cohesion measurement between a content item and a hyperlinked landing page are presented. In one embodiment, a plurality of content item signals is generated for the content item and a corresponding plurality of signals are generated for the hyperlinked landing page. An analysis of the corresponding signals is conducted to determine a measurement of topic cohesion, a topic cohesion score, between the content item and the hyperlinked landing page. A cohesion predictor model is trained to generate the predictive topic cohesion score between an input content item and a hyperlinked landing page. Upon a determination that the topic cohesion score is less than a predetermined threshold, remedial actions are taken regarding the hyperlink of the content item. Alternatively, positive actions may be carried out, including promoting the content item to others, associating advertisements with the content item, and the like.