# US 2019/0356956 A1 · Intelligent viewer sentiment predictor for digital media content streams

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0356956 A1
- Document ID: US20190356956A1
- Status: Published application
- Kind: A1
- Application number: 16/411,972
- Filed: 2019-05-14
- Published: 2019-11-21
- Earliest claimed: 2018-05-15
- Assignees: BroadbandTV, Corp.
- Applicants: BROADBANDTV, Corp.
- Inventors: Jiaqi SHENG; Mehrdad FATOURECHI; Di Xu
- Web page: https://patentgrep.com/patent/US20190356956A1

## CPC

- H04N 21/4667: {Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections}
- G06N 20/00: Machine learning
- G06Q 30/0271: {Personalized advertisement}
- H04N 21/23418: {involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)}
- H04N 21/251: {Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08)}
- H04N 21/25883: {being end-user demographical data, e.g. age, family status or address (arrangements for identifying locations of users in broadcast systems H04H60/52)}
- H04N 21/25891: {being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)}
- H04N 21/4532: {involving end-user characteristics, e.g. viewer profile, preferences (monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18)}
- H04N 21/4665: {involving classification methods, e.g. Decision trees}
- H04N 21/812: {involving advertisement data (advertising per se G06Q30/02)}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

The herein disclosed technology provides methods and systems for intelligently predicting viewer sentiments invoked by a collection of digital content (e.g., a web-based digital channel) based on an assessment of channel metadata, such as channel metadata defining an association between the channel and one or more other channels; channel history data for the channel; and demographic information about the channel.

## Claims

### Claim 1

A method of predicting viewer sentiment invoked by a collection of digital content items accessible through a digital content channel, the method comprising:
assessing channel metadata associated with the collection of digital content items, the channel metadata including at least one of:
data indicating an association between the channel and one or more other channels;
channel history data for the channel; and
demographic information about the channel;
determining a channel risk metric for the digital content channel based on the assessment of the channel metadata; and
rendering to a display a sentiment prediction based on the channel risk metric.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the channel risk metric further comprises:
providing the channel metadata to a machine learning classifier trained on a dataset comprising a channel metadata and a predetermined risk quantifier for each of multiple digital channels, the machine learning classifier configured to receive channel metadata for a source channel and output a channel metrics sentiment indicator qualifying a negative sentiment risk for the source channel.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the channel risk metric further comprises:
computing a channel history sentiment indicator based on changes in a quantity of content accessible through the digital content channel, wherein a net increase in the quantity of content accessible through the digital content channel is associated with a lower negative sentiment risk than a sentiment score associated with a net decrease in the quantity of content accessible through the digital content channel.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the channel risk metric further comprises:
computing a channel history sentiment indicator based on a viewing statistic for the digital content channel, the viewing statistic quantifying changes in viewing time for the digital content channel, wherein a net decrease in viewing time is associated with a higher negative sentiment risk than a sentiment score associated with a net increase in the viewing time.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining the channel risk metric further comprises:
computing a channel association sentiment indicator based on a channel status for each of multiple other digital content channels managed by users subscribed to the digital content channel, the channel association sentiment indicator being indicative of a greater negative sentiment risk when a larger proportion of the other digital content channels are disabled than when a smaller proportion of the other user channels are disabled.

### Claim 6 (depends on 1)

The method of claim 1, wherein the sentiment prediction is further based on a visual risk metric quantifying negative sentiment risk associated with visual content of the digital content channel and a textual risk metric quantifying a negative sentiment risk associated with textual content of the digital content channel.

### Claim 7 (depends on 1)

The method of claim 1, wherein the sentiment prediction is a quantifier defined in association with a predefined risk category.

### Claim 8

A system for predicting viewer sentiment invoked by a collection of digital content items accessible through a digital content channel, the system comprising:
memory;
a processor;
a sentiment prediction engine stored in the memory and executable by the processor to assess channel metadata associated with the collection of digital content items to determine and render to a display a channel risk metric quantifying a negative sentiment risk for the digital content channel, the channel metadata including at least one of:
data defining an association between the channel and one or more other channels;
channel history data for the channel; and
demographic information about the channel.

### Claim 9 (depends on 8)

The system of claim 8, wherein the sentiment prediction engine renders the channel risk metric utilizing a machine learning classifier trained on a dataset comprising a channel metadata and a predetermined risk quantifier for each of multiple digital channels, the machine learning classifier configured to receive channel metadata for a source channel and output a channel metrics sentiment indicator qualifying a negative sentiment risk for the source channel.

### Claim 10 (depends on 8)

The system of claim 8, wherein the sentiment prediction engine renders the channel risk metric by computing a channel history sentiment indicator based on changes in a quantity of content accessible through the digital content channel over time, wherein a net increase in the quantity of content accessible through the digital content channel is associated with a lower negative sentiment risk than a sentiment score associated with a net decrease in the quantity of content accessible through the digital content channel.

### Claim 11 (depends on 8)

The system of claim 8, wherein the sentiment prediction engine renders the channel risk metric by computing a channel history sentiment indicator based on a viewing statistic for the digital content channel, the viewing statistic quantifying changes in viewing time for the digital content channel, wherein a net decrease in the viewing time is associated with a higher negative sentiment risk than a sentiment score associated with a net increase in the viewing time.

### Claim 12 (depends on 8)

The system of claim 8, wherein the sentiment prediction engine renders the channel risk metric by computing a channel association sentiment indicator based on a channel status for each of multiple other digital content channels managed by users subscribed to the digital content channel, the channel association sentiment indicator being indicative of a greater negative sentiment risk when a larger proportion of the other digital content channels are disabled than when a smaller proportion of the other user channels are disabled.

### Claim 13 (depends on 8)

The system of claim 8, wherein the sentiment prediction engine further renders the channel risk metric based on at least one of a visual risk metric quantifying negative sentiment risk associated with visual content of the digital content channel and a textual risk metric quantifying a negative sentiment risk associated with textual content of the digital content channel and an audio risk metric quantifying negative sentiment risk associated with audio content of the digital content channel.

### Claim 14 (depends on 8)

The system of claim 8, wherein the sentiment prediction is a quantifier defined in association with a predefined risk category.

### Claim 15

One or more memory devices encoding computer-executable instructions for executing a computer process for predicting viewer sentiment invoked by a collection of digital content items accessible through a digital content channel, the computer process comprising:
assessing channel metadata associated with the collection of digital content items, the channel metadata including at least one of:
data defining an association between the channel and one or more other channels;
channel history data for the channel; and
demographic information about the channel;
determining a channel risk metric for the digital content channel based on the assessment of the channel metadata; and
rendering to a display a sentiment prediction based on the channel risk metric.

### Claim 16 (depends on 15)

The one or more memory devices of claim 15, wherein determining the channel risk metric further comprises:
providing the channel metadata to a machine learning classifier trained on a dataset comprising a channel metadata and a predetermined risk quantifier for each of multiple digital channels, the machine learning classifier configured to receive channel metadata for a source channel and output a channel metrics sentiment indicator qualifying a negative sentiment risk for the source channel.

### Claim 17 (depends on 15)

The one or more memory devices of claim 15, wherein determining the channel risk metric further comprises:
computing a channel history sentiment indicator based on changes in a quantity of content accessible through the digital content channel, wherein a net increase in the quantity of content accessible through the digital content channel is associated with a lower negative sentiment risk than a sentiment score associated with a net decrease in the quantity of content accessible through the digital content channel.

### Claim 18 (depends on 15)

The one or more memory devices of claim 15, wherein determining the channel risk metric further comprises:
computing a channel history sentiment indicator based on a viewing statistic for the digital content channel, the viewing statistic quantifying changes in viewing time for the digital content channel, wherein a net decrease in the viewing time is associated with a higher negative sentiment risk than a sentiment score associated with a net increase in the viewing time.

### Claim 19 (depends on 15)

The one or more memory devices of claim 15, wherein determining the channel risk metric further comprises:
computing a channel association sentiment indicator based on a channel status for each of multiple other digital content channels managed by users subscribed to the digital content channel, the channel association sentiment indicator being indicative of a greater negative sentiment risk when a larger proportion of the other digital content channels are disabled than when a smaller proportion of the other user channels are disabled.

### Claim 20 (depends on 15)

The one or more memory devices of claim 15, wherein the sentiment prediction is further based on a visual risk metric quantifying negative sentiment risk associated with visual content of the digital content channel and a textual risk metric quantifying a negative sentiment risk associated with textual content of the digital content channel.
