Machine-based content analysis and user perception tracking of microcontent messages

• US 9,304,989 B2
• Filed: 12/08/2014
• Issued: 04/05/2016
• Est. Priority Date: 02/17/2012
• Status: Expired due to Fees

• Current Assignee: Blazent Incorporated (ServiceNow Incorporated)
• Original Assignee: Bottlenose, Inc. (ServiceNow Incorporated)
• Inventors: Spivack, Nova, Heide, Dominiek ter
• Primary Examiner(s): Ditren, Belix M Ortiz
• Application Number:
  US14/563,875
• Publication Number:
  US 20150095021A1
• Time in Patent Office: 484 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/211 Schema design and management
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A system and a method for microcontent natural language processing are presented. The method comprising steps of receiving a microcontent message from a social networking server, tokenizing the microcontent message into one or more text tokens, performing a topic extraction on the microcontent message to extract topic metadata, generating sentiment metadata for the microcontent message, analyzing co-occurrence of all available metadatas in the plurality of microcontent messages, producing a list that ranks the plurality of microcontent messages based on all available topic metadata, and compiling a trend database that reveals how perception of users of the social networking server on a given topic changes by tracking how the list changes over time.

Claims

1. A method for microcontent natural language processing comprising:

receiving a plurality of microcontent messages from a social networking server, the plurality of microcontent messages including a microcontent message;

breaking up the microcontent message into one or more text tokens by using a tokenizer module that is configured to process micro-syntax and punctuation in the microcontent message;

performing a part-of-speech (POS) tagging process on the text tokens to identify a linguistic category for each of the text tokens, wherein the POS tagging process for a respective text token is performed using an error-driven transformation-based tagger and based on a definition and a context of the respective text token;

performing a topic extraction on the microcontent message to extract topic metadata for the microcontent message based on the identified linguistic category for each of the text tokens, wherein the extraction is performed without looking up a pre-specified topic in a dictionary of known entities;

associating a topic metadata to the microcontent message based on the extracted topic;

generating sentiment metadata for the microcontent message by performing a sentiment analysis on the one or more text tokens to classify a sentiment of the microcontent message, wherein the sentiment analysis is based on a Naï

ve Bayesian classifier;

associating the sentiment metadata with the microcontent message;

analyzing co-occurrence of all available metadata in the plurality of microcontent messages;

producing a list that ranks the plurality of microcontent messages based on all available topic metadata and sentiment metadata associated with the plurality of microcontent messages; and

compiling a trend database that reveals how perception of users of the social networking server on a given topic changes by tracking how the list changes over time.

2. The method of claim 1, wherein the Naï

ve Bayesian classifier is trained offline on an annotated set of positive, negative and neutral messages.

3. The method of claim 1, further comprising:

identifying type metadata from the microcontent message based on an ontology of predetermined microcontent types by applying a database of annotation rules to the text tokens of the microcontent message; and

associating the identified type metadata to the microcontent message;

wherein the ontology of predetermined microcontent types are organized as a relational database including trees of the predetermined microcontent types.

4. The method of claim 3, wherein the annotation rules include lists of names and patterns that help assigning a tree of the trees of the predetermined microcontent types to the microcontent message.

5. The method of claim 3, further comprising:

providing an interface for users to edit the ontology of predetermined microcontent types or the database of annotation rules.

6. The method of claim 3, wherein the step of identifying type metadata of the microcontent message includes:

compiling a matching index including a set of expressions based on the ontology of predetermined microcontent types or the database of annotation rules; and

matching the expressions of the matching index with the microcontent message.

7. The method of claim 1, further comprising:

performing a language detection on the microcontent message to detect language metadata; and

associating the detected language metadata with the microcontent message.

8. The method of claim 7, wherein the language detection is based on a dictionary-based language detector or an NGram language detector.

9. The method of claim 1, further comprising:

performing a speech tagging on the microcontent message to identify nouns in the microcontent message.

10. The method of claim 9, wherein the speech tagging is based on a Brill tagger method.

11. The method of claim 1, further comprising:

assigning a confidence score for each piece of the extracted topic metadata; and

associating the confidence scores the topic metadata associated with the microcontent message.

12. The method of claim 1, further comprising:

presenting, via a user interface, the list of trending topics as scatters in a quadrant scatter plot, wherein a volume of a respective scatter indicates a size of a trending topic represented by the respective scatter.

13. A system comprising:

a network component configured for receiving a plurality of microcontent messages from a social networking server, the plurality of microcontent messages including a microcontent message;

a processor; and

a memory storing instructions which, when executed by the processor, cause the system to perform a process including;

breaking up the microcontent message into one or more text tokens by using a tokenizer module that is configured to process micro-syntax and punctuation in the microcontent message;

performing a part-of-speech (POS) tagging process on the text tokens to identify a linguistic category for each of the text tokens, wherein the POS tagging process for a respective text token is performed using an error-driven transformation-based tagger and based on a definition and a context of the respective text token;

performing a topic extraction on the microcontent message to extract topic metadata for the microcontent message based on the identified linguistic category for each of the text tokens, wherein the extraction is performed without looking up a pre-specified topic in a dictionary of known entities;

associating a topic metadata to the microcontent message based on the extracted topic;

generating sentiment metadata for the microcontent message by performing a sentiment analysis on the one or more text tokens to classify a sentiment of the microcontent message, wherein the sentiment analysis is based on a Naï

ve Bayesian classifier;

associating the sentiment metadata with the microcontent message;

analyzing co-occurrence of all available metadata in the plurality of microcontent messages;

producing a list that ranks the plurality of microcontent messages based on all available topic metadata and sentiment metadata associated with the plurality of microcontent messages; and

compiling a trend database that reveals how perception of users of the social networking server on a given topic changes by tracking how the list changes over time.

14. The system of claim 13, wherein the process further includes:

identifying type metadata from the microcontent message based on an ontology of predetermined microcontent types by applying a database of annotation rules to the text tokens of the microcontent message; and

associating the identified type metadata to the microcontent message.

15. The system of claim 14, wherein the step of identifying type metadata of the microcontent message includes:

compiling a matching index including a set of expressions based on the ontology of predetermined microcontent types or the database of annotation rules; and

matching the expressions of the matching index with the microcontent message.

16. The system of claim 13, wherein the process further includes:

performing a language detection on the microcontent message to detect language metadata, wherein the language detection is based on a dictionary-based language detector or an NGram language detector; and

associating the detected language metadata with the microcontent message.

17. The system of claim 13, wherein the process further includes:

performing a speech tagging on the microcontent message to identify nouns in the microcontent message, wherein the speech tagging is based on a Brill tagger method.

18. The system of claim 13, wherein the process further includes:

presenting, via a user interface, the list of trending topics as scatters in a quadrant scatter plot, wherein a volume of a respective scatter indicates a size of a trending topic represented by the respective scatter; and

producing an animation of the quadrant scatter plot over a time period to reflect how the trending topics change in the plurality of microcontent messages.

19. The system of claim 13, wherein the process further includes:

producing an animation of the quadrant scatter plot over a time period to reflect how the trending topics change in the plurality of microcontent messages.