Trend detection for content targeting using an information distribution system

Patent metadata

Field	Value
Publication number	US-11290413-B2
Application number	US-202016866162-A
Country	US
Kind code	B2
Filing date	May 4, 2020
Priority date	Jul 3, 2015
Publication date	Mar 29, 2022
Grant date	Mar 29, 2022

Abstract

In some examples, a method includes receiving, from one or more client devices, a stream of messages composed by one or more users of the one or more client devices, wherein each of the messages includes a particular hashtag, determining, using a set of metrics that are based at least in part on the messages, a trending score that represents a magnitude of a trend for the particular hashtag, in response to determining that the trending score satisfies a threshold, sending, to a content provider system, a set of demographic data that describes one or more of the users who associated with the particular hashtag, and, in response to receiving, from the content provider system, targeted content that is based at least in part on the particular hashtag and the set of demographic data, sending, for display at the one or more of the one or more client devices, the targeted content.

First claim

What is claimed is:

1. A method, comprising:
receiving an indication of a predetermined topic of interest;
receiving a plurality of messages composed by a plurality of users of one or more client devices, wherein each message in a first set of messages in the plurality of messages includes a first hashtag and respective first semantic content, wherein the first hashtag corresponds to the topic, wherein each message in a second set of messages in the plurality of messages includes a second hashtag and respective second semantic content, wherein at least some messages of the second set of messages do not include the first hashtag, and wherein at least some messages of the first set of messages do not include the second hashtag;
determining that the second hashtag corresponds to the topic by:
calculating a degree of similarity between the first semantic content of the messages in the first set of messages and the second semantic content of the messages in the second set of messages; and
determining that the second hashtag corresponds to the topic when the degree of similarity exceeds a similarity threshold;
calculating, based on one or more metrics for the first set of messages and for the second set of messages, a trending score that represents a magnitude of a trend for the topic; and

when the trending score exceeds a trending threshold, transmitting a) an indication of the topic, and b) demographic information for the first set of users composing the first set of messages including the first hashtag and for the second set of users composing the second set of messages including the second hashtag to a content provider system.

2. The method of claim 1 , wherein the second hashtag is one of a set of second hashtags, each second hashtag corresponding to a different set of messages of the plurality of messages, the determining that the second hashtag corresponds to the topic further including determining that each second hashtag of the set of second hashtags corresponds to the topic by:
calculating, for that second hashtag, the degree of similarity for that second hashtag between the first semantic content of the messages in the first set of messages and semantic content of the set of messages that include that second hashtag; and
determining that that second hashtag corresponds to the topic when the degree of similarity for that second hashtag exceeds the similarity threshold,
the calculating further including calculating the trending score based on the one or more metrics for the first set of messages and each set of messages corresponding to one of the second hashtags of the set of second hashtags.

3. The method of claim 1 , further comprising calculating the one or more metrics, the one or more metrics including an acceleration metric, the acceleration metric being a measure of a rate of change in a rate of distribution of all messages including the first hashtag, the second hashtag, or both per unit of time during a predetermined time period.

4. The method of claim 1 , further comprising calculating the one or more metrics, the one or more metrics including a nodality metric, the nodality metric being a measure of how many users are following other users that have shared or re-shared all messages including the first hashtag, the second hashtag, or both, per unit time during a predetermined time period.

5. The method of claim 1 , further comprising calculating the one or more metrics, the one or more metrics including a velocity metric, the velocity metric being a measure of a rate of distribution of all messages including the first hashtag, the second hashtag, or both, per unit of time during a predetermined time period.

6. The method of claim 1 further comprising, prior to the transmitting, aggregating the demographic information based on one or more of, for each user of the second plurality of users, age, gender, location, history of content generated by that user, history of content read by that user, history of content followed by that user, one or more hashtags previously used by that user, or one or more mention tags used by that user, the transmitting including transmitting the aggregated demographic information.

7. The method of claim 1 further comprising, prior to the transmitting, dividing the demographic information based on one or more of, for each user of the plurality of users, age, gender, location, history of content generated by that user, history of content read by that user, history of content followed by that user, one or more hashtags previously used by that user, or one or more mention tags used by that user, the transmitting including transmitting the divided demographic information.

8. The method of claim 1 , the calculating further including:
generating a feature vector based on the one or more metrics; and
calculating the trending score by providing the feature vector to a trained machine learning model and receiving, from the machine learning model, the trending score based on the feature vector.

9. The method of claim 8 , further comprising training the machine learning model, prior to the calculating, based on training sets of metrics and corresponding training scores.

10. The method of claim 8 , further comprising training the machine learning model, during the calculating, based on training sets of metrics and corresponding training scores.

11. The method of claim 8 , further comprising training the machine learning model based on historical sets of metrics and corresponding historical scores.

12. The method of claim 8 , further comprising training the machine learning model based on a degree of error between the calculated trending score and an indication of an actual trending score.

13. A system comprising:
one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving an indication of a predetermined topic of interest;
receiving a plurality of messages composed by a plurality of users of one or more client devices, wherein each message in a first set of messages in the plurality of messages includes a first hashtag and respective first semantic content, wherein the first hashtag corresponds to the topic, wherein each message in a second set of messages in the plurality of messages includes a second hashtag and respective second semantic content, wherein at least some messages of the second set of messages do not include the first hashtag, and wherein at least some messages of the first set of messages do not include the second hashtag;
determining that the second hashtag corresponds to the topic by:
calculating a degree of similarity between the first semantic content of the messages in the first set of messages and the second semantic content of the messages in the second set of messages; and
determining that the second hashtag corresponds to the topic when the degree of similarity exceeds a similarity threshold;
calculating, based on one or more metrics for the first hashtag and for the second hashtag, a trending score that represents a magnitude of a trend for the topic; and

when the trending score exceeds a trending threshold, transmitting a) an indication of the topic, and b) demographic information for the first set of users composing the first set of messages including the first hashtag and for the second set of users composing the second set of messages including the second hashtag to a content provider system.

14. The system of claim 13 , wherein the instructions are further executable by the one or more computers

Assignees

• Twitter Inc

Inventors

• Jain Dinkar
• Lin Mu
• Hotchkiss David

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• H04L51/52 Primary

  for supporting social networking services · CPC title

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title