Back to results
US 11,417,131 B2Granted
Techniques for sentiment analysis of data using a convolutional neural network and a co-occurrence network
AssigneeOracle International Corporation
InventorsMichael Malak, Mark L. Kreider
Life of this patent
Estimating the term…
Abstract
Techniques are provided for performing sentiment analysis on words in a first data set. An example embodiment includes generating a word embedding model including a first plurality of features. A value indicating sentiment for the words in the first data set can be determined using a convolutional neural network (CNN). A second plurality of features are generated based on bigrams identified in the data set. The bigrams can be generated using a co-occurrence graph. The model is updated to include the second plurality of features, and sentiment analysis can be performed on a second data set using the updated model.
Claims20
A method comprising, at a computer system:
- training a word embedding model based on training data;
- generating the word embedding model comprising a first plurality of features for words based on the trained word embedding model;
- generating an initial matrix, wherein the initial matrix comprises a plurality of rows comprising a plurality of words from a first data set, and a first plurality of columns comprising the first plurality of features from the word embedding model;
- determining one or more values indicating a measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features, wherein the one or more values indicating the measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features are determined using a convolutional neural network;
- generating a co-occurrence graph based on the first data set which is used to generate the initial matrix;
- identifying one or more bigrams in the first data set based on the co-occurrence graph that was generated based on the first data set;
- determining a set of bigrams in the co-occurrence graph, that was generated based on the first data set, having a highest frequency of occurrence;
- generating an updated matrix to include a second plurality of features corresponding with the set of bigrams having the highest frequency of occurrence;
- for each of the second plurality of features, generating, in the updated matrix, an indication of an occurrence of a bigram corresponding to each the plurality of words based on the set of bigrams and the co-occurrence graph;
- and
- determining a measure of sentiment for a second data set using the updated matrix.
8 more elements
A system comprising:
- one or more processors;
- a memory accessible to the one or more processors, the memory comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform a method comprising:
- training a word embedding model based on training data;
- generating the word embedding model comprising a first plurality of features for words based on the trained word embedding model;
- generating an initial matrix, wherein the initial matrix comprises a plurality of rows comprising a plurality of words from a first data set, and a first plurality of columns comprising the first plurality of features from the word embedding model;
- determining one or more values indicating a measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features, wherein the one or more values indicating the measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features are determined using a convolutional neural network;
- generating a co-occurrence graph based on the first data set which is used to generate the initial matrix;
- identifying one or more bigrams in the first data set based on the co-occurrence graph that was generated based on the first data set;
- determining a set of bigrams in the co-occurrence graph, that was generated based on the first data set, having a highest frequency of occurrence;
- generating an updated matrix to include a second plurality of features corresponding with the set of bigrams having the highest frequency of occurrence;
- for each of the second plurality of features, generating, in the updated matrix, an indication of an occurrence of a bigram corresponding to each the plurality of words based on the set of bigrams and the co-occurrence graph;
- and
- determining a measure of sentiment for a second data set using the updated matrix.
10 more elements
A non-transitory computer readable medium storing a plurality of instructions for controlling a computer system to perform a method comprising:
- training a word embedding model based on training data;
- generating the word embedding model comprising a first plurality of features for words based on the trained word embedding model;
- generating an initial matrix, wherein the initial matrix comprises a plurality of rows comprising a plurality of words from a first data set, and a first plurality of columns comprising the first plurality of features from the word embedding model;
- determining one or more values indicating a measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features, wherein the one or more values indicating the measure of sentiment for the plurality of words in the initial matrix in relation to each of the first plurality of features are determined using a convolutional neural network;
- generating a co-occurrence graph based on the first data set which is used to generate the initial matrix;
- identifying one or more bigrams in the first data set based on the co-occurrence graph that was generated based on the first data set;
- determining a set of bigrams in the co-occurrence graph, that was generated based on the first data set, having a highest frequency of occurrence;
- generating an updated matrix to include a second plurality of features corresponding with the set of bigrams having the highest frequency of occurrence;
- for each of the second plurality of features, generating, in the updated matrix, an indication of an occurrence of a bigram corresponding to each the plurality of words based on the set of bigrams and the co-occurrence graph;
- and
- determining a measure of sentiment for a second data set using the updated matrix.
8 more elements
Dependencies are inferred from the claim text.