VISUALIZING RESULTS OF ELECTRONIC SENTIMENT ANALYSIS

• US 20160350644A1
• Filed: 12/11/2015
• Published: 12/01/2016
• Est. Priority Date: 05/29/2015
• Status: Abandoned Application

• Current Assignee: SAS Institute Incorporated, North Carolina State University (University of North Carolina System)
• Original Assignee: SAS Institute Incorporated, North Carolina State University (University of North Carolina System)
• Inventors: Caira, David James, Healey, Christopher G., Dinakaran, Gowtham, Padia, Kalpesh, Devarajan, Ravinder, Benson, Jordan Riley, Sethi, Saratendu, Cox, James Allen
• Application Number:
  US14/966,380
• Publication Number:
  US 20160350644A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

The results of electronic sentiment analysis can be visualized. For example, multiple sentiments expressed in an electronic communication can be determined using a neural network. Each sentiment of the multiple sentiments can include a positive sentiment, a neutral sentiment, or a negative sentiment. A transition between at least two sentiments of the multiple sentiments can be determined. The transition can indicate a change between the at least two sentiments occurring over a period of time. A graphical user interface visually indicating the transition between the at least two sentiments can be displayed on a timeline. The timeline can include a timeframe associated with multiple segments of the electronic communication.

Claims

1. A non-transitory computer readable medium comprising program code executable by a processor for causing the processor to:

determine a plurality of sentiments expressed in an electronic communication using a neural network, each sentiment of the plurality of sentiments comprising a positive sentiment, a neutral sentiment, or a negative sentiment;

determine a transition between at least two sentiments of the plurality of sentiments, the transition indicating a change between the at least two sentiments occurring over a period of time;

display a graphical user interface (GUI) visually indicating the transition between the at least two sentiments on a timeline, the timeline comprising a timeframe associated with a plurality of segments of the electronic communication;

display the timeline as a graph within the GUI; and

plot on the graph a plurality of points associated with the plurality of sentiments expressed in the electronic communication.

3. The non-transitory computer readable medium of claim 1, further comprising program code executable by the processor for causing the processor to:

plot on the graph the plurality of points associated with the plurality of sentiments expressed in the electronic communication by;

obtaining a plurality of comments from the electronic communication; and

positioning each point of the plurality of points on the graph in a location indicative of a sentiment expressed in a particular comment of the plurality of comments.

4. The non-transitory computer readable medium of claim 3, further comprising program code executable by the processor for causing the processor to:

position each point of the plurality of points on the graph in the location indicative of the sentiment expressed in the particular comment of the plurality of comments by;

positioning a respective point on the graph above a reference line in response to the sentiment being positive, on the reference line in response to the sentiment being neutral, or below the reference line in response to the sentiment being negative.

5. The non-transitory computer readable medium of claim 4, further comprising program code executable by the processor for causing the processor to:

display the plurality of comments within the GUI;

receive a user input indicating a selection of a particular point on the graph; and

in response to the user input, visually highlight a comment of the plurality of comments corresponding to the particular point.

6. The non-transitory computer readable medium of claim 5, further comprising program code executable by the processor for causing the processor to:

visually highlight the comment of the plurality of comments corresponding to the particular point by;

displaying a graphical object comprising the comment adjacent to the particular point on the graph.

7. The non-transitory computer readable medium of claim 5, further comprising program code executable by the processor for causing the processor to:

in response to the user input, display an indicator of a source of the comment corresponding to the particular point.

8. The non-transitory computer readable medium of claim 4, further comprising program code executable by the processor for causing the processor to:

receive a user input indicating that a point of the plurality of points on the graph corresponds to an incorrect sentiment;

move the point to a new position on the graph indicating a correct sentiment; and

retrain the neural network based on the correct sentiment.

9. The non-transitory computer readable medium of claim 1, further comprising program code executable by the processor for causing the processor to:

receive the electronic communication from a text message, an e-mail, a social media post, a tweet, a blog post, or a forum post.

2. (canceled)

10. A method comprising:

determining a plurality of sentiments expressed in an electronic communication using a neural network, each sentiment of the plurality of sentiments comprising a positive sentiment, a neutral sentiment, or a negative sentiment;

determining a transition between at least two sentiments of the plurality of sentiments, the transition indicating a change between the at least two sentiments occurring over a period of time;

displaying a graphical user interface (GUI) visually indicating the transition between the at least two sentiments on a timeline, the timeline comprising a timeframe associated with a plurality of segments of the electronic communication;

displaying the timeline as a graph within the GUI; and

plotting on the graph a plurality of points associated with the plurality of sentiments expressed in the electronic communication.

12. The method of claim 10, further comprising:

plotting on the graph the plurality of points associated with the plurality of sentiments expressed in the electronic communication by;

obtaining a plurality of comments from the electronic communication; and

positioning each point of the plurality of points on the graph in a location indicative of a sentiment expressed in a particular comment of the plurality of comments.

13. The method of claim 12, further comprising:

positioning each point of the plurality of points in the location indicative of the sentiment expressed in the particular comment of the plurality of comments by;

positioning a respective point on the graph above a reference line in response to the sentiment being positive, on the reference line in response to the sentiment being neutral, or below the reference line in response to the sentiment being negative.

14. The method of claim 13, further comprising:

displaying the plurality of comments within the GUI;

receiving a user input indicating a selection of a particular point on the graph; and

in response to the user input, visually highlighting a comment of the plurality of comments corresponding to the particular point.

15. The method of claim 14, further comprising:

visually highlighting the comment of the plurality of comments corresponding to the particular point by;

displaying a graphical object comprising the comment adjacent to the particular point on the graph.

16. The method of claim 14, further comprising:

in response to the user input, displaying an indicator of a source of the comment corresponding to the particular point.

17. The method of claim 13, further comprising:

receiving a user input indicating that a point of the plurality of points on the graph corresponds to an incorrect sentiment;

moving the point to a new position on the graph indicating a correct sentiment; and

retraining the neural network based on the correct sentiment.

18. The method of claim 10, further comprising:

receiving the electronic communication from a text message, an e-mail, a social media post, a tweet, a blog post, or a forum post.

11. (canceled)

19. A system comprising:

a processing device; and

a memory device in which instructions executable by the processing device are stored for causing the processing device to;

determine a plurality of sentiments expressed in an electronic communication using a neural network, each sentiment of the plurality of sentiments comprising a positive sentiment, a neutral sentiment, or a negative sentiment;

determine a transition between at least two sentiments of the plurality of sentiments, the transition indicating a change between the at least two sentiments occurring over a period of time;

display a graphical user interface (GUI) visually indicating the transition between the at least two sentiments on a timeline, the timeline comprising a timeframe associated with a plurality of segments of the electronic communication;

display the timeline as a graph within the GUI; and

plot on the graph a plurality of points associated with the plurality of sentiments expressed in the electronic communication.

21. The system of claim 19, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

plot on the graph the plurality of points associated with the plurality of sentiments expressed in the electronic communication by;

obtaining a plurality of comments from the electronic communication; and

positioning each point of the plurality of points on the graph in a location indicative of a sentiment expressed in a particular comment of the plurality of comments.

22. The system of claim 21, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

position each point of the plurality of points in the location indicative of the sentiment expressed in the particular comment of the plurality of comments by;

positioning a respective point on the graph above a reference line in response to the sentiment being positive, on the reference line in response to the sentiment being neutral, or below the reference line in response to the sentiment being negative.

23. The system of claim 22, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

display the plurality of comments within the GUI;

receive a user input indicating a selection of a particular point on the graph; and

in response to the user input, visually highlight a comment of the plurality of comments corresponding to the particular point.

24. The system of claim 23, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

visually highlight the comment of the plurality of comments corresponding to the particular point by;

displaying a graphical object comprising the comment adjacent to the particular point on the graph.

25. The system of claim 23, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

in response to the user input, display an indicator of a source of the comment corresponding to the particular point.

26. The system of claim 22, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

receive a user input indicating that a point of the plurality of points on the graph corresponds to an incorrect sentiment;

move the point to a new position on the graph indicating a correct sentiment; and

retrain the neural network based on the correct sentiment.

20. (canceled)

27. The system of claim 20, wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

receive the electronic communication from a text message, an e-mail, a social media post, a tweet, a blog post, or a forum post.