Automated emotional clustering of social media conversations

1. A computer-implemented real-time, emotional-monitoring system for brands and companies, comprising a computer system comprising hardware and software, said computer system implementing the steps of obtaining real-time social media conversations, inputting said real-time social media conversations into the computer system, wherein the software automatically classifies, categorizes and summarizes expressed emotions in said real-time social media conversations by using a knowledge base of emotional words, or phrases, or both words and phrases as an input, wherein the knowledge base comprises a list of emotional tokens and pairwise token distance using a degree of similarity, each pair associated with a valence and arousal score expressed on a scale, defining a continuous distance metric between said real-time social media conversations comprising same or different number of the emotional tokens utilizing an expand-align-compare (EAC) algorithm, conducting hierarchical clustering based on that distance metric, and outputting a result associated with said hierarchical clustering.

2. A computer-implemented method for real-time, emotional-monitoring system for brands and companies, comprising the steps of obtaining real-time social media conversations, inputting said real-time social media conversations into a computer system comprising software that automatically classifies, categorizes and summarizes expressed emotions in said real-time social media conversations by using a knowledge base of emotional words, or phrases, or both words and phrases as an input, wherein the knowledge base comprises a list of emotional tokens and pairwise token distance using a degree of similarity, each pair associated with a valence and arousal score expressed on a scale, defining a continuous distance metric between said real-time social media conversations comprising same or different number of the emotional tokens utilizing an expand-align-compare (EAC) algorithm, conducting hierarchical clustering based on that distance metric, and outputting a result associated with said hierarchical clustering.

3. Non-transitory computer readable media storing computer code that, when executed, performs the computer-implemented method of claim 2 .

4. A social media intelligence platform comprising:

a. a processor providing an analyst application comprising:

i. a first software module obtaining real-time social media conversations;

ii. a second software module automatically classifying, categorizing and summarizing expressed emotions in said real-time social media conversations by using a knowledge base of emotional words, or phrases, or both words and phrases as an input, wherein the knowledge base comprises a list of emotional tokens and pairwise token distance using a degree of similarity, each pair associated with a valence and arousal score expressed on a scale;

iii. a third software module defining a continuous distance metric between said real-time social media conversations comprising same or different number of the emotional tokens utilizing an expand-align-compare (EAC) algorithm; and

iv. a fourth software module conducting clustering based on that distance metric;

b. the processor further providing a customer dashboard application comprising:

i. a fifth software module providing an interface allowing the customer to input a topic; and

ii. a sixth software module providing a graphic visualization of the sentiment clusters for the topic.

5. The platform of claim 4 , wherein the social media comprises a blog, microblog, social network, podcast, wiki, content community, virtual world, or a combination thereof.

6. The platform of claim 4 , wherein the knowledge base is domain-specific.

7. The platform of claim 6 , wherein the domain is entertainment.

8. The platform of claim 4 , wherein the knowledge base further comprises words or phrases not expressing sentiment.

9. The platform of claim 4 , wherein the analyst application further comprises a software module associating equivalents with at least one of the tokens.

10. The platform of claim 9 , wherein the equivalents comprise synonyms or misspellings.

11. The platform of claim 4 , wherein the analyst application further comprises a software module calibrating the tokens by assigning a valence and arousal score.

12. The platform of claim 11 , wherein the valence and arousal scores are derived from a sample of social media communications containing at least one of the tokens.

13. The platform of claim 4 , wherein the number of sentiment clusters is dynamically determined based on the content of the social media communications.

14. The platform of claim 4 , wherein the graphic visualization of sentiment clusters comprises one or more prototypical communications associated with each cluster.

15. The platform of claim 4 , wherein the customer dashboard application is offered as software-as-a-service.

16. A computer-implemented social media intelligence system comprising:

a. a digital processor performing a computer program comprising executable instructions stored on a memory device;

b. the computer program providing a social media intelligence application comprising:

i. a first software module obtaining real-time social media conversations;

ii. a second software module automatically classifying, categorizing and summarizing expressed emotions in said real-time social media conversations by using a knowledge base of emotional words, or phrases, or both words and phrases as an input, wherein the knowledge base comprises a list of emotional tokens and pairwise token distance using a degree of similarity, each pair associated with a valence and arousal score expressed on a scale;

iii. a third software module defining a continuous distance metric between said real-time social media conversations comprising same or different number of the emotional tokens utilizing an expand-align-compare (EAC) algorithm;

iv. a fourth software module conducting hierarchical clustering based on that distance metric; and

vi. a fifth software module outputting a result associated with said hierarchical clustering.

17. The system of claim 16 , wherein the social media comprises a blog, microblog, social network, podcast, wiki, content community, virtual world, or a combination thereof.

18. The system of claim 16 , wherein the knowledge base is domain-specific.

19. The system of claim 18 , wherein the domain is entertainment.

20. The system of claim 16 , wherein the knowledge base further comprises words or phrases not expressing sentiment.

21. The system of claim 16 , wherein at least one of the tokens is associated with at least one equivalent.

22. The system of claim 21 , wherein an equivalent comprises a synonym or a misspelling.

23. The system of claim 16 , wherein the valence and arousal scores are derived from a sample of social media communications containing at least one of the tokens.

24. The system of claim 16 , wherein the number of clusters is dynamically determined based on the content of the social media communications.

25. The system of claim 16 , wherein the result comprises a graphic visualization of the clusters.

26. Non-transitory computer-readable storage media encoded with a computer program including instructions executable by a processor to provide a social media intelligence application comprising:

a. a first software module obtaining real-time social media conversations;

b. a second software module automatically classifying, categorizing and summarizing expressed emotions in said real-time social media conversations by using a knowledge base of emotional words, or phrases, or both words and phrases as an input, wherein the knowledge base comprises a list of emotional tokens and pairwise token distance using a degree of similarity, each pair associated with a valence and arousal score expressed on a scale;

c. a third software module defining a continuous distance metric between said real-time social media conversations comprising same or different number of the emotional tokens utilizing an expand-align-compare (EAC) algorithm;

d. a fourth software module conducting hierarchical clustering based on that distance metric; and

e. a fifth software module outputting a result associated with said hierarchical clustering.

27. The media of claim 26 , wherein the social media comprises a blog, microblog, social network, podcast, wiki, content community, virtual world, or a combination thereof.

28. The media of claim 26 , wherein the knowledge base is domain-specific.

29. The media of claim 28 , wherein the domain is entertainment.

30. The media of claim 26 , wherein the knowledge base further comprises words or phrases not expressing sentiment.

31. The media of claim 26 , wherein at least one of the tokens is associated with at least one equivalent.

32. The media of claim 31 , wherein an equivalent comprises a synonym or a misspelling.

33. The media of claim 26 , wherein the valence and arousal scores are derived from a sample of social media communications containing at least one of the tokens.

34. The media of claim 26 , wherein the number of clusters is dynamically determined based on the content of the social media communications.

35. The media of claim 26 , wherein the result comprises a graphic visualization of the clusters.