Features for automatic classification of narrative point of view and diegesis
First Claim
Patent Images
1. A computer-based system of predicting a narrative point of view of text data, the system comprising:
- a receiving device configured to receive text data;
a non-transitory computer-readable medium comprising natural language processing code stored thereon that, when executed, cause a processor to;
receive, by the receiving device, text data;
perform feature extraction using feature extraction code, by performing the following;
remove quoted text and punctuation characters from the text data;
convert upper case characters in the text data to lower case characters;
extract each pronoun contained in the text data and a respective number of instances of each pronoun;
insert a respective number of instances of each pronoun into a feature vector; and
predict, by support vector machine code, a narrative point of view of the text data based upon the extracted pronouns and the respective number of instances of each pronoun,wherein each pronoun comprises one of the following;
“
I”
, “
me”
, “
my”
, “
mine”
, “
myself”
, “
we”
, “
us”
, “
our”
, “
ours”
, “
you”
, “
your”
, “
yours”
, “
he”
, “
him”
, “
his”
, “
she”
, “
her”
, “
hers”
, “
they”
, “
them”
, and “
theirs”
, andwherein the support vector machine code is trained to predict the narrative point of view of the text data based upon the pronouns and the respective number of instances of each pronoun.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods for classifying a point of view and diegesis are provided. A method can include providing a processor in operable communication with a computer-readable medium, receiving a narrative text, extracting a set of features from the narrative text, transmitting the features into a feature vector, transmitting a plurality of feature vectors to a support vector machine, predicting a point of view and diegesis for the narrative text associate with a particular feature vector, and annotating the narrative text.
24 Citations
13 Claims
-
1. A computer-based system of predicting a narrative point of view of text data, the system comprising:
-
a receiving device configured to receive text data; a non-transitory computer-readable medium comprising natural language processing code stored thereon that, when executed, cause a processor to; receive, by the receiving device, text data; perform feature extraction using feature extraction code, by performing the following; remove quoted text and punctuation characters from the text data; convert upper case characters in the text data to lower case characters; extract each pronoun contained in the text data and a respective number of instances of each pronoun; insert a respective number of instances of each pronoun into a feature vector; and predict, by support vector machine code, a narrative point of view of the text data based upon the extracted pronouns and the respective number of instances of each pronoun, wherein each pronoun comprises one of the following;
“
I”
, “
me”
, “
my”
, “
mine”
, “
myself”
, “
we”
, “
us”
, “
our”
, “
ours”
, “
you”
, “
your”
, “
yours”
, “
he”
, “
him”
, “
his”
, “
she”
, “
her”
, “
hers”
, “
they”
, “
them”
, and “
theirs”
, andwherein the support vector machine code is trained to predict the narrative point of view of the text data based upon the pronouns and the respective number of instances of each pronoun. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A computer-based system of predicting a diegesis of text data, the system comprising:
-
a receiving device configured to receive text data; a non-transitory computer-readable medium comprising natural language processing code stored thereon that, when executed, cause a processor to; receive, by a receiving device, text data; perform feature extraction using feature extraction code, by performing the following; remove quoted text and punctuation characters from the text data; convert upper case characters in the narrative text to lower case characters; extract each pronoun contained in the text data, a respective number of instances of each pronoun, and a respective number of instances of each first person pronoun appearing in an argument of a verb; insert each the respective number of instances of each pronoun and the respective number of instances of each first person pronoun appearing in an argument of a verb into a feature vector; and predict, by support vector machine code, a diegesis of the text data based upon the extracted pronouns, the respective number of instances of each pronoun, and the respective number of instances of each first person pronoun appearing in an argument of a verb, wherein each pronoun comprises one of the following;
“
I”
, “
me”
, “
my”
, “
mine”
, “
myself”
, “
we”
, “
us”
, “
our”
, “
ours”
, “
you”
, “
your”
, “
yours”
, “
he”
, “
him”
, “
his”
, “
she”
, “
her”
, “
hers”
, “
they”
, “
them”
, and “
theirs”
, andwherein the support vector machine code is trained to predict the diegesis of the text data based upon the pronouns, the respective number of instances of each pronoun, and the respective number of instances of each first person pronoun appearing in an argument of a verb. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A non-transitory computer-readable medium having stored thereon that, when executed, cause a processor to:
-
receive text data; remove quoted text and punctuation characters from the text data; separate each sentence from the text data; tokenize the separated sentences; convert upper case characters in the text data to lower case characters; extract pronouns from the text data, each respective pronoun comprising one of the following;
“
I”
, “
me”
, “
mine”
, “
myself”
, “
we”
, “
us”
, “
ours”
, “
you”
, “
your”
, “
yours”
, “
he”
, “
him”
, “
his”
, “
she”
, “
her”
, “
hers”
, “
they”
, “
them”
, and “
theirs”
, a respective number of instances of each pronoun, and a respective number of instances of each first person pronoun appearing in an argument of a verb;receive a plurality of labels, the labels comprising first person point of view, third person point of view, homodiegetic, and heterodiegetic, homodiegetic representing a narrator being personally involved in the narrative text, and heterodiegetic representing a narrator personally uninvolved in the narrative text; insert each the respective number of instances of each pronoun and the respective number of instances of each first person pronoun appearing in an argument of a verb into a respective feature vector; and access a support vector machine contained in, or in operable communication with, the processor, the support vector machine being configured to; receive a plurality of feature vectors, receive the plurality of labels; generate support vectors from the set plurality of feature vectors; generate a hyperplane from the support vectors, the hyperplane being configured to provide a maximum margin between the hyperplane the support vectors; associate a feature vector of the plurality of feature vectors with a label; and predict a label from the plurality of labels to associate with an unlabeled feature vector.
-
Specification