Generating persuasive electronic messages using interplay of message content features

Patent metadata

Field	Value
Publication number	US-2018143986-A1
Application number	US-201615355673-A
Country	US
Kind code	A1
Filing date	Nov 18, 2016
Priority date	Nov 18, 2016
Publication date	May 24, 2018
Grant date	—

Abstract

The present disclosure is directed towards methods and systems for determining a persuasiveness of a content item. The systems and methods receive a content item from a client device and analyze the content item. Analyzing the content item includes analyzing at least one textual element, at least one image element, and at least one layout element of the content item to determine a first persuasion score, a second persuasion score, and a third persuasion score of the elements the content item. The systems and methods also generate a persuasion score of the content item and provide the persuasion score of the content item to the client device.

First claim

We claim:

1 . A method of determining persuasiveness of a user-authored digital content item, the method comprising:
receiving a content item; analyzing, by at least one processor, the content item, wherein analyzing the content item comprises:
analyzing a textual element of the content item to determine a first characteristic score corresponding to the at least one textual element of the content item;
analyzing an image element of the content item to determine a second characteristic score corresponding to the image element of the content item; and
analyzing a layout element of the content item to determine a third characteristic score corresponding to the layout element of the content item;
performing a step for determining a persuasion score of the content item using the first characteristic score, the second characteristic score, and the third characteristic score; and providing the persuasion score of the content item for display to a user.

2 . The method of claim 1 , further comprising:
identifying a set of intended recipients of the content item; analyzing characteristics associated with each intended recipient within the set of intended recipients to determine a fourth characteristic score corresponding to each intended recipient, wherein the step for determining the persuasion score of the content item further uses the fourth characteristic score corresponding to each intended recipient.

3 . The method of claim 2 , wherein identifying a set of intended recipients of the content item comprises selecting the set of intended recipients based on the content item.

4 . The method of claim 2 , wherein analyzing characteristics associated with each intended recipient of the content item to determine a fourth characteristic score comprises determining at least one of a gender of the intended recipient, an income level of the intended recipient, a time since a last interaction with a previous content item by the intended recipient, or a time since a registration of the intended recipient.

5 . The method of claim 2 , wherein identifying a set of intended recipients of the content item comprises to identifying the set of intended recipients from a database of potential recipients.

6 . The method of claim 1 , wherein analyzing the textual element of the content item to determine a first characteristic score comprises determining a text readability, a text formality, or a text sentiment of the textual element.

7 . The method of claim 1 , wherein analyzing the image element of the content item to determine a second characteristic score comprises determining an image memorability or an image aesthetic of the image element.

8 . The method of claim 7 , wherein determining the image aesthetic of the image element of the content item comprises analyzing one or more of an image organization, object repetition, a depth of field, a lighting, a symmetry, a color scheme, motion blur, an object emphasis, and a color harmony of the at least one image element of the content item.

9 . The method of claim 1 , wherein analyzing the layout element of the content item to determine a third characteristic score comprises determining a proportion of an area corresponding to the image element with respect to a total area of the content item.

10 . The method of claim 1 , wherein analyzing the layout element of the content item to determine a third characteristic score comprises determining a relative position of the image element within the content item.

11 . A system comprising:
a memory comprising a database of potential recipients of a content item, wherein the database of potential recipients comprises attribute information associated with each potential recipient of the potential recipient users; and a computer device communicatively coupled to the memory, the computer device storing instructions that, when executed by at least one processor, cause the computer device to:
access the database of potential recipients for the content item;
determine a plurality of element characteristic scores for a content item by analyzing elements within the content item;
determine a plurality of recipient characteristic scores for each intended recipient within a set of intended recipients by accessing attribute information associated with each intended recipient within the database of potential recipients;
determine interaction probabilities for the set of intended recipients by using the plurality of element characteristic scores and the plurality of recipient characteristic scores for each intended recipient, wherein a given interaction probability relates to a given intended recipient from the set of intended recipients; and
determining a persuasion score for the content item by analyzing the interaction probabilities over all intended recipients within the set of intended recipients.

12 . The system of claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer device to analyze the content item to identify the plurality of elements within the content item.

13 . The system of claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer device to identify the set of intended recipients from the database of potential recipients.

14 . The system of claim 11 , wherein determining interaction probabilities for the set of intended recipients by using the plurality of element characteristic scores and the plurality of recipient characteristic scores comprises:
assigning weights to each element score of the plurality of element scores to obtain a plurality of weighted element scores; assigning weights to each recipient characteristic score of the plurality of recipient characteristic scores to obtain a plurality of weighted recipient characteristic scores; and combining the weighted element scores and the weighted recipient characteristic scores to determine the interaction probabilities for the set of intended recipients.

15 . The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computer device to adjust the interaction probabilities for the set of intended recipients by applying a correction factor.

16 . The system of claim 15 , wherein the persuasion score for the content item represents a predicted interaction rate of the content item for the set of intended recipients.

17 . A method of determining the persuasiveness of a user-authored digital content item, the method comprising:
receiving an electronic communication comprising a plurality of content items; analyzing, by at least one processor, each content item of the plurality of content items within the electronic communication; based on analyzing each content item, determining a persuasion score for each content item of the plurality of content items within the electronic communication; and determining an overall persuasion score of the electronic communication based on the persuasion score of each content item of the plurality of content items.

18 . The method of claim 17 , further comprising:
determining a proportion of an area within the electronic communication that corresponds to each content item of the plurality of content items within the electronic communication; and generating a weighted persuasion score for each content item of the plurality of content items, wherein the weighted persuasion score is based on the proportion of the display area that corresponds to each content item.

Assignees

• Adobe Systems Inc

Inventors

• Sinha Moumita
• Gupta Varun
• Sengupta Tathagata
• Ganguly Niloy
• Ahmad Faran

Classifications

• G06F17/30684

  Physics · mapped topic

• G06F17/3071 Primary

  Physics · mapped topic

• G06F17/30716

  Physics · mapped topic

• G06Q30/0242 Primary

  Determining effectiveness of advertisements · CPC title