Abstract: A method and a system for natural language processing of digital content objects, such as news stories, which ranks named entities in digital content objects by the impact that digital content objects that mention them are having on social media, is provided. Digital content objects are scored on a per object basis based on social media activity metrics associated with that digital content object. Named entities that appear in each digital content object are also extracted through natural language analysis. The named entities are then scored on a per entity basis to obtain an entity score that the object scores of those digital content objects in which that named entity appears. An entity ranking list can be created based on the entity scores, which can then be used in various different ways. For example, the entity ranking list can be displayed on a graphical user interface.
Type:
Grant
Filed:
July 31, 2017
Date of Patent:
September 15, 2020
Assignee:
Newswhip Media Limited
Inventors:
Andrew Mullaney, Bojan Furlan, Katrin Braunschweig
Abstract: A method and system for processing digital content objects, such as news stories, are provided. A user specifies digital content objects of interest. The user specification is then applied to a source of digital content objects in order to obtain a batch of digital content objects matching the specification. A value of a variable, such as a social media impact metric, is then determined for each of the digital content objects of the batch and these values are fitted to a distribution function in order to determine parameter values for the distribution function. A threshold value for alerting is then determined based on the parameterized distribution function. The specification can then continue to be applied to the source of digital content objects and when new digital content objects are found that match the specification, their values are compared against the threshold value for alerting and the user is alerted only in respect of new digital content objects that have values which exceed the threshold value.
Abstract: A system of tracking rate of change of social network activity associated with a digital object includes a change measurement module in communication with at least one social network database and a ranking module in communication with the change measurement module. The change measurement module measures a change in the level of social network activity associated with the digital object based on a first object value and a second object value. The first object value is based on a measurement of activity associated with the digital object in at least one social network at a first time, and the second object value is based on a measurement of activity at a second time. The ranking module ranks the digital object relative to at least one other digital object based on a score derived from a rate of change in social network activity.