Methods, apparatuses and computer program products for joint use of speech and text-based features for sentiment detection

• US 8,918,320 B2
• Filed: 01/03/2012
• Issued: 12/23/2014
• Est. Priority Date: 01/03/2012
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Adler, Mark, Kiss, Imre Attila, Mairesse, Francois, Polifroni, Joseph
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US13/342,684
• Publication Number:
  US 20130173269A1
• Time in Patent Office: 1,085 Days
• Field of Search: 704/246, 704/247, 704/251, 704/252, 704/257
• US Class Current: 704/251
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G10L 25/24 the extracted parameters being the cepstrum
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals

Abstract

An apparatus for generating a review based in part on detected sentiment may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including determining a location(s) of the apparatus and a time(s) that the location(s) was determined responsive to capturing voice data of speech content associated with spoken reviews of entities. The computer program code may further cause the apparatus to analyze textual and acoustic data corresponding to the voice data to detect whether the textual or acoustic data includes words indicating a sentiment(s) of a user speaking the speech content. The computer program code may further cause the apparatus to generate a review of an entity corresponding to a spoken review(s) based on assigning a predefined sentiment to a word(s) responsive to detecting that the word indicates the sentiment of the user. Corresponding methods and computer program products are also provided.

Claims

1. A method comprising:

determining one or more locations of a device and one or more times that the locations were determined in response to capturing voice data of speech content associated with one or more spoken reviews of one or more entities;

analyzing textual data and acoustic data corresponding to the voice data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content; and

generating, via a processor, a review of at least one of the entities corresponding to one of the spoken reviews based in part on assigning at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user.

2. The method of claim 1, wherein prior to generating the review, the method further comprises:

analyzing textual words of the textual data to assign a textual sentiment to the word and analyzing spoken words of the acoustic data to assign an acoustic sentiment to the word based on detecting that the word indicates the sentiment of the user; and

utilizing the textual sentiment and the acoustic sentiment in the assigning of the predefined sentiment to the word, the sentiment of the user denotes at least one opinion of the user regarding the entity.

3. The method of claim 1, wherein generating the review further comprises determining that the predefined sentiment is associated with at least one attribute of the entity and assigning a rating to the attribute based on the predefined sentiment, the assigned rating is included in the generated review.

4. The method of claim 1, wherein determining further comprises determining the locations and times simultaneously with the capturing of the respective spoken reviews.

5. The method of claim 1, further comprising:

generating at least one profile on behalf of the user, the profile comprises information indicating the locations, the times and the spoken reviews.

6. The method of claim 5, further comprising:

analyzing the information of the profile to determine one or more preferences of the user.

7. The method of claim 5, further comprising:

using the information of the profile to provide recommended entities to the user of a same or similar type as an entity identified in the profile in an instance in which the user is subsequently in a location near a location of the entity.

8. The method of claim 5, further comprising:

determining an identity of an entity based on the location information of the profile in an instance in which the identity is indiscernible from the voice data;

determining that the generated review comprises a review of the identified entity; and

associating the identified entity with the generated review.

9. The method of claim 5, further comprising:

providing suggested times to attend one or more events at one or more entities based in part on information indicating the times and locations of the profile in response to determining that the user is in one of the locations.

10. The method of claim 5, further comprising:

providing recommended entities to devices of other users based in part on the information of the profile of the user.

11. An apparatus comprising:

at least one processor; and

at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following;

determine one or more locations of the apparatus and one or more times that the locations were determined in response to capturing voice data of speech content associated with one or more spoken reviews of one or more entities;

analyze textual data and acoustic data corresponding to the voice data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content; and

generate a review of at least one of the entities corresponding to one of the spoken reviews based in part on assigning at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user.

12. The apparatus of claim 11, wherein prior to generate the review, the memory and computer program code are configured to, with the processor, cause the apparatus to:

analyze textual words of the textual data to assign a textual sentiment to the word and analyze spoken words of the acoustic data to assign an acoustic sentiment to the word based on detecting that the word indicates the sentiment of the user; and

utilize the textual sentiment and the acoustic sentiment in the assigning of the predefined sentiment to the word, the sentiment of the user denotes at least one opinion of the user regarding the entity.

13. The apparatus of claim 11, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

generate the review by determining that the predefined sentiment is associated with at least one attribute of the entity; and

assign a rating to the attribute based on the predefined sentiment, the assigned rating is included in the generated review.

14. The apparatus of claim 11, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

determine the locations and times by detecting the locations and times simultaneously with the capturing of the respective spoken reviews.

15. The apparatus of claim 11, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

generate at least one profile on behalf of the user, the profile comprises information indicating the locations, the times and the spoken reviews.

16. The apparatus of claim 15, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

analyze the information of the profile to determine one or more preferences of the user.

17. The apparatus of claim 15, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

utilize the information of the profile to provide recommended entities to the user of a same or similar type as an entity identified in the profile in an instance in which the user is subsequently in a location near a location of the entity.

18. The apparatus of claim 15, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

determine an identity of an entity based on the location information of the profile in an instance in which the identity is indiscernible from the voice data;

determine that the generated review comprises a review of the identified entity; and

associate the identified entity with the generated review.

19. The apparatus of claim 15, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

provide suggested times to attend one or more events at one or more entities based in part on information indicating the times and locations of the profile in response to determining that the user is in one of the locations.

20. The apparatus of claim 15, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

provide recommended entities to devices of other users based in part on the information of the profile of the user.

21. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions in response to execution by a processor causes an apparatus to at least:

determine one or more locations of a device and one or more times that the locations were determined in response to capturing voice data of speech content associated with one or more spoken reviews of one or more entities;

analyze textual data and acoustic data corresponding to the voice data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content; and

generate a review of at least one of the entities corresponding to one of the spoken reviews based in part on assigning at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user.

22. The computer program product of claim 21, wherein the computer-readable program code portions in response to execution by the processor further causes the apparatus to:

analyze textual words of the textual data to assign a textual sentiment to the word and spoken words of the acoustic data to assign an acoustic sentiment to the word based on detecting that the word indicates the sentiment of the user; and

utilize the textual sentiment and the acoustic sentiment in the assigning of the predefined sentiment to the word, the sentiment of the user denotes at least one opinion of the user regarding the entity.