US2013268321A1PendingUtilityA1

Emotivity and Vocality Measurement

Individually held — no corporate assignee on recordPriority: Apr 12, 2009Filed: Apr 25, 2013Published: Oct 10, 2013
Est. expiryApr 12, 2029(~2.7 yrs left)· nominal 20-yr term from priority
G06Q 30/0203G06Q 30/02
53
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

One embodiment of the present invention is directed to a computer-implemented system that analyzes free-form text comments provided by a user (such as a customer of a company) and draws conclusions about the tone of the user's feedback, such as whether the user's feedback is positive, negative, angry, critical, or congratulatory. Such conclusions may be reflected in a single numerical value referred to herein as “emotivity.” A customer's emotivity score may be used for various purposes, such as determining whether the customer is likely to provide a positive testimonial for the company, or whether a follow-up phone call should be made to the customer to improve the company's relationship with the customer. Furthermore, a measurement of the customer's loyalty to the company may be modified based on the user's measured emotivity.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A computer-implemented method comprising:
 (A) providing a survey to a plurality of people, the survey comprising a plurality of questions;   (B) receiving, from the plurality of people, a plurality of sets of answers to the plurality of questions;   (C) identifying a plurality of loyalty indices of the plurality of people based on the plurality of sets of answers;   (D) for each of the plurality of people U:
 (D)(1) identifying text input T associated with person U; 
 (D)(2) identifying a count E of words in text input T which are in a set of words representing strong emotions; 
 (D)(3) identifying a count P of words in text input T which are in a set of words representing positive emotions; 
 (D)(4) identifying a count N of words in text input T which are in a set of words representing negative emotions; and 
   (E) selecting values of coefficients A, B, and C that maximize a value of R 2  between the plurality of loyalty indices and values of a variable Emo for the plurality of people, wherein Emo=A*E+B*P+C*N.

Join the waitlist — get patent alerts

Track US2013268321A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.