USING MEDIA INFORMATION FOR IMPROVING DIRECT MARKETING RESPONSE RATE

• US 20140244359A1
• Filed: 02/22/2013
• Published: 08/28/2014
• Est. Priority Date: 02/22/2013
• Status: Active Grant

• Current Assignee: DoorDash, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Mahmud, Jalal U., HABER, Eben M.
• Granted Patent: US 10,460,334 B2
• Time in Patent Office: Days
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

Embodiments of the invention relate to improving direct marketing response rate through use of media information. One embodiment includes extracting samples of language usage in one or more social media activities. Language usage features comprising relationships to products are derived by analyzing the extracted samples for relevant language terms. The language usage features are mapped to one or more of personality traits, emotional state and personal features. The mapped language usage features and personal features are stored in a repository. Customers are segmented for direct marketing using the mapped language usage features and the personal features.

Claims

1. A method comprising:

extracting samples of language usage in one or more social media activities;

deriving language usage features comprising relationships to products by analyzing the extracted samples for relevant language terms;

mapping the language usage features to one or more of personality traits, emotional state or personal features;

storing the mapped language usage features and personal features in a repository; and

segmenting customers for direct marketing using the mapped language usage features and personal features.

2. The method of claim 1, wherein the social media activities comprise one or more of writing activities and speech interactions.

3. The method of claim 2, wherein the writing activities comprise one or more of social media written interaction, personality questionnaires or surveys.

4. The method of claim 3, wherein the speech interactions comprise speech used in interactions with a call center.

5. The method of claim 4, wherein the personality traits are mapped using one or more of Big 5 and linguistic inquiry and word count (LIWC) techniques.

6. The method of claim 4, further comprising using the personal features for prediction modeling a probability of customer response to direct marketing.

7. The method of claim 6, further comprising:

extracting time and date information when the media activities were conducted;

deriving activity patterns based on statistics for the extracted time and date information; and

performing further segmentation of the customers for direct marketing using the derived activity patterns.

8. The method of claim 6, wherein language use comprises language related to one or more of product names and competing product names, and the relationships to products comprises one or more of an indication for liking or disliking, indication of ownership, and indication of intent to purchase.

9. A method comprising:

extracting samples of language usage in one or more social media activities;

determining a likelihood of product interest in one or more products by analyzing the extracted samples for a relationship to a product based on language terms;

predicting a response to product marketing using a prediction model that is generated based on the determined likelihood of product interest; and

segmenting customers for direct marketing based on the predicted response.

10. The method of claim 9, wherein determining the likelihood of product interest is based on language usage comprising one or more of product mention, competing product mention, and purchase intent.

11. The method of claim 10, wherein the social media activities comprise one or more of social media writing activities and speech interactions, and the relationship to the product comprises one or more of an indication of liking the product, an indication of disliking the product, product ownership, and an indication of intent to purchase the product.

12. The method of claim 11, wherein the determining likelihood of product interest comprises:

using one or more of Big 5 and linguistic inquiry and word count (LIWC) techniques for mapping the language usage to one or more of personality traits, emotional state or personal features.

13. The method of claim 12, further comprising modeling a probability of customer response to direct marketing using the test marketing heuristics and the likelihood of product interest.

14. The method of claim 13, further comprising:

extracting time and date information when the social media activities were conducted;

deriving activity patterns based on statistics for the extracted time and date information; and

performing further segmentation of the customers for direct marketing using the derived activity patterns.

15. A method comprising:

extracting samples of language usage in one or more social media activities;

extracting time and date information for the samples of language usage based on when the one or more social media activities were conducted;

deriving temporal activity patterns based on statistics for the extracted time and date information;

modeling probability of customer response to a direct marketing activity based on derived temporal activity patterns; and

performing segmentation of contacts for direct marketing using the modeled probability and derived temporal activity patterns.

16. The method of claim 15, further comprising determining a likelihood of product interest based on the language usage, wherein the language usage comprises one or more of product mention, competing product mention, and purchase intent.

17. The method of claim 16, wherein the social media activities comprise one or more of social media writing activities and speech interactions.

18. The method of claim 17, wherein the determining likelihood of product interest comprises:

using one or more of Big 5 and linguistic inquiry and word count (LIWC) techniques for mapping the language usage to one or more of personality traits, emotional state and personal features.

19. The method of claim 18, further comprising:

deriving language usage features comprising relationships to products by analyzing extracted media usage samples for relevant language terms;

mapping the language usage features to one or more of personality traits, emotional state or personal features; and

using the mapped language usage features and the derived temporal activity patterns for segmenting of contacts for test marketing campaigns.

20. The method of claim 19, wherein results of the test marketing campaigns are used for future direct marketing activities based on determining correlations between one or more of demographics, personality traits, emotional state, derived language features and derived temporal activity patterns.