Predicting personality traits based on text-speech hybrid data

Abstract

Techniques for generating a personality trait model are described. According to an example, a system is provided that can generate text data and linguistic data, and apply psycholinguistic data to the text data and the linguistic data, resulting in updated text data and updated linguistic data. The system is further operable to combine the updated text data with the updated linguistic data to generate a personality trait model. In various embodiments, the personality trait model can be trained and updated as additional data is received from various inputs.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 generating, by a device operatively coupled to a processor, text-speech hybrid data associated with a user, wherein the generating comprises:
 combining according to respective defined weights:
 tone data comprising linguistic characteristics of a voice of the user in 
 
 voice data from verbal input of the user, and
 text data representative of speech data from the verbal input of a user, 
 
 wherein the text data is augmented with psycholinguistic data; and 
   training, by the device, a personality model based on the text-speech hybrid data to determine at least one personality trait of the user.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 training, by the device, the personality model based further on personality trait data.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the psycholinguistic data comprises first psycholinguistic data, the computer-implemented method further comprising:
 generating, by the device, second psycholinguistic data from social media data; and   using, by the device, the second psycholinguistic data to generate the personality trait data.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 training, by the device, the personality model based further on emotion data related to an emotion derived from the tone data.   
     
     
         5 . The computer-implemented method of  claim 1 , further comprising:
 training, by the device, the personality model based further on emotion data related to an emotion derived from the text data.   
     
     
         6 . The computer-implemented method of  claim 1 , wherein the respective defined weights are determined based on:
 determining a reliability of the tone data as a factor for determining the at least one personality trait;   determining the respective defined weights based on the reliability.   
     
     
         7 . The computer-implemented method of  claim 1 , further comprising:
 generating, by the device based on the at least one personality trait, a recommendation for the user associated with a service.   
     
     
         8 . A system, comprising:
 a memory that stores computer executable components; and   a processor operably coupled to the processor and that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
 a combination component that generates text-speech hybrid data associated with a user based on combining according to respective defined weights:
 tone data comprising linguistic characteristics of a voice of the user in voice data from verbal input of the user, and 
 text data representative of speech data from the verbal input of a user, wherein the text data is augmented with psycholinguistic data; and 
 
 a training component that trains a personality model based on the text-speech hybrid data to determine at least one personality trait of the user. 
   
     
     
         9 . The system of  claim 8 , wherein the training component trains the personality model based further on personality trait data. 
     
     
         10 . The system of  claim 9 , wherein the psycholinguistic data comprises first psycholinguistic data, and the combination component:
 generates second psycholinguistic data from social media data; and   generates the personality trait data based on the second psycholinguistic data.   
     
     
         11 . The system of  claim 8 , wherein the training component trains the personality model based further on emotion data related to an emotion derived from the tone data. 
     
     
         12 . The system of  claim 8 , wherein the training component trains the personality model based further on emotion data related to an emotion derived from the text data. 
     
     
         13 . The system of  claim 8 , wherein the combination component further:
 determines a reliability of the tone data as a factor for determining the at least one personality trait; and   determines the respective defined weights based on the reliability.   
     
     
         14 . The computer-implemented method of  claim 1 , further comprising:
 a model generation output component that generates, based on the at least one personality trait, a recommendation for the user associated with a service.   
     
     
         15 . A computer program product for generating a personality model, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
 generate text-speech hybrid data associated with a user, wherein the generating comprises:
 combining according to respective defined weights:
 tone data comprising linguistic characteristics of a voice of the user in voice data from verbal input of the user, and 
 text data representative of speech data from the verbal input of a user, 
 
 wherein the text data is augmented with psycholinguistic data; and 
   train a personality model based on the text-speech hybrid data to determine at least one personality trait of the user.   
     
     
         16 . The computer program product of  claim 15 , wherein the program instructions are further executable by the device to cause the device to:
 training, by the device, the personality model based further on personality trait data.   
     
     
         17 . The computer program product of  claim 16 , wherein the program instructions are further executable by the device to cause the device to:
 generate second psycholinguistic data from social media data; and   generate the personality trait data based on the second psycholinguistic data.   
     
     
         18 . The computer program product of  claim 15 , wherein the program instructions are further executable by the device to cause the device to:
 train the personality model based further on emotion data related to an emotion derived from the tone data.   
     
     
         19 . The computer program product of  claim 15 , wherein the program instructions are further executable by the device to cause the device to:
 train the personality model based further on emotion data related to an emotion derived from the text data.   
     
     
         20 . The computer program product of  claim 15 , wherein the program instructions are further executable by the device to cause the device to:
 determine a reliability of the tone data as a factor for determining the at least one personality trait; and   determine the respective defined weights based on the reliability.