Method and system for generating a transitory sentiment community

1. A method, performed in a processor of a server computing device, of generating a transitory sentiment community, the method comprising:

identifying, in accordance with a supervised trained model, within agglomerated social media content data, content associated with a subject of interest and characterized in accordance with one of a sentiment expressive usage and not a sentiment expressive usage, the subject of interest defined in accordance with at least one text character string;

performing, based on an unsupervised trained model in conjunction with content associated with the sentiment expressive usage, a sentiment analysis that determines a sentiment intensity rating associated with at least a portion of the agglomerated social media content data; and

generating the transitory sentiment community based at least in part on the sentiment intensity rating.

2. The method of claim 1 wherein the agglomerated social media content comprises one or more of: a hashtag, a twitter handle, an emoticon, at least a portion of a website content, a product brand name, a product feature, a message exchange, an image, a video portion, and a text string produced via a speech to text conversion of at least a portion of an audio file source.

3. The method of claim 1 further comprising generating the transitory sentiment community based on the subject of interest as embedded into the agglomerated social media content data.

4. The method of claim 1 further comprising generating the transitory sentiment community based on at least one of amplifying and attenuating the sentiment intensity rating.

5. The method of claim 4 further comprising generating the transitory sentiment community based on at least one of amplifying and attenuating the sentiment intensity rating based in part on at least one of: (i) a personality trait associated with an author of the content associated with the sentiment expressive usage, and (ii) upon detecting existence of a slang expression in the content associated with the sentiment expressive usage.

6. The method of claim 1 wherein the generating is based on applying a sentiment intensity threshold to the sentiment intensity rating, the sentiment intensity rating being one of above and below the sentiment intensity threshold.

7. The method of claim 1 further comprising:

generating the transitory sentiment community based on a set of sentiment classifications, respective ones of the set of sentiment classifications being associated with a respective sentiment intensity threshold; and

modifying at least one of the set of sentiment classifications to one or more alternate sentiment classifications recognized by the unsupervised training model.

8. The method of claim 1 wherein at least one of the supervised and the unsupervised trained model is trained, in accordance with a neural network machine learning model comprising a set of input layers interconnected via a set of intermediate layers to an output layer, the machine learning neural network model being instantiated in the processor based at least in part upon processor-executable instructions being accessed by the processor from a non-transitory memory.

9. The method of claim 8 , wherein training the supervised trained model comprises:

providing the agglomerated social media content to the set of input layers of the machine learning neural network, the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the machine learning neural network, upon providing of content predetermined as being associated with the subject of interest to the output layer, based at least in part upon recursively adjusting the initial matrix of weights by backpropagation in diminishment of an error matrix computed at the output layer.

10. The method of claim 8 , wherein training the unsupervised trained model comprises:

providing content identified as being associated with the subject of interest to the set of input layers of the machine learning neural network, the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the machine learning neural network based at least in part upon recursively adjusting the initial matrix of weights backpropagation in diminishment of an error matrix computed in accordance with a sentiment intensity rating generated at the output layer.

11. A server computing system for generating a transitory sentiment community, the server computing system comprising:

a processor;

a memory storing a set of instructions, the instructions when executed in the processor causing operations comprising:

identifying, in accordance with a supervised trained model, within agglomerated social media content data, content associated with a subject of interest and characterized in accordance with one of a sentiment expressive usage and not a sentiment expressive usage, the subject of interest defined in accordance with at least one text character string;

performing, based on an unsupervised trained model in conjunction with content associated with the sentiment expressive usage, a sentiment analysis that determines a sentiment intensity rating associated with at least a portion of the agglomerated social media content data; and

generating the transitory sentiment community based at least in part on the sentiment intensity rating.

12. The server computing system of claim 11 wherein the agglomerated social media content comprises one or more of: a hashtag, a twitter handle, an emoticon, at least a portion of a website content, a product brand name, a product feature, a message exchange, an image, a video portion, and a text string produced via a speech to text conversion of at least a portion of an audio file source.

13. The server computing system of claim 11 further comprising executable instructions causing operations comprising generating the transitory sentiment community based on the subject of interest as embedded into the agglomerated social media content data.

14. The server computing system of claim 11 further comprising executable instructions causing operations comprising generating the transitory sentiment community based on at least one of amplifying and attenuating the sentiment intensity rating.

15. The server computing system of claim 14 further comprising executable instructions causing operations comprising generating the transitory sentiment community based on at least one of amplifying and attenuating the sentiment intensity rating based in part on at least one of: (i) a personality trait associated with an author of the content associated with the sentiment expressive usage, and (ii) upon detecting existence of a slang expression in the content associated with the sentiment expressive usage.

16. The server computing system of claim 11 wherein the generating is based on applying a sentiment intensity threshold to the sentiment intensity rating, the sentiment intensity rating being one of above and below the sentiment intensity threshold.

17. The server computing system of claim 11 further comprising executable instructions causing operations comprising:

generating the transitory sentiment community based on a set of sentiment classifications, respective ones of the set of sentiment classifications being associated with a respective sentiment intensity threshold; and

modifying at least one of the set of sentiment classifications to one or more alternate sentiment classifications recognized by the unsupervised training model.

18. The server computing system of claim 11 wherein at least one of the supervised and the unsupervised trained model is trained, in accordance with a neural network machine learning model comprising a set of input layers interconnected via a set of intermediate layers to an output layer, the machine learning neural network model being instantiated in the processor based at least in part upon processor-executable instructions being accessed by the processor from a non-transitory memory.

19. The server computing system of claim 18 , wherein training the supervised trained model comprises:

providing the agglomerated social media content to the set of input layers of the machine learning neural network, the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the machine learning neural network, upon providing of content predetermined as being associated with the subject of interest to the output layer, based at least in part upon recursively adjusting the initial matrix of weights by backpropagation in diminishment of an error matrix computed at the output layer.

20. The server computing system of claim 18 , wherein training the supervised trained model comprises:

providing content identified as being associated with the subject of interest to the set of input layers of the machine learning neural network, the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the machine learning neural network based at least in part upon recursively adjusting the initial matrix of weights by backpropagation in diminishment of an error matrix computed in accordance with a sentiment intensity rating generated at the output layer.