Tracking message topics in an interactive messaging environment

• US 8,924,491 B2
• Filed: 02/23/2012
• Issued: 12/30/2014
• Est. Priority Date: 02/28/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cai, Keke, Guo, HongLei, Su, Zhong, Zhu, Hui Jia
• Primary Examiner(s): Nguyen, Dustin
• Assistant Examiner(s): NGUYEN, HAO HONG
• Application Number:
  US13/403,472
• Publication Number:
  US 20120221656A1
• Time in Patent Office: 1,041 Days
• US Class Current: 709/206
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

A method and apparatus for tracking a topic involved in a message in an interactive messaging environment containing a plurality of messages by combining with context messages associated with the message. The method includes the steps of: selecting a message from the plurality of messages contained in the interactive messaging environment; identifying context messages associated with the selected message from the plurality of messages contained in the interactive messaging environment; and grouping the selected message into one or more topic groups based on the identified context messages. The topic tracking method and apparatus of the invention can accurately determine similarities between messages in an interactive messaging environment such as microblog to perform topic tracking.

Claims

1. A method for tracking message topics in an interactive messaging environment, wherein the interactive messaging environment contains a plurality of messages, the method comprising the steps of:

selecting a message from the plurality of messages contained in the interactive messaging environment;

determining a predetermined topic field of topics to be tracked;

for each of a plurality of users;

acquiring topic preferences of the user by analyzing interactive operations of the user in the interactive messaging environment;

comparing the acquired topic preferences of the user with the determined predetermined topic field; and

identifying the user as an interactive operation user associated with the selected message if the topic preferences of the user match the predetermined topic field;

identifying, from messages corresponding to each of one or more identified interactive operation users, messages having replying or forwarding relations with the selected message, as context messages associated with the selected message;

extracting one or more context topic keywords from the identified context messages;

generating one or more topic keywords by processing the extracted context topic keywords; and

grouping the selected message into one or more topic groups corresponding to the generated one or more topic keywords respectively,

wherein at least one of the steps is carried out by a computer device.

2. The method according to claim 1, wherein the generating step comprises:

extracting, from the selected message, one or more kernel topic keywords; and

generating one or more topic keywords by combining the extracted kernel topic keywords and the extracted context topic keywords.

3. The method according to claim 1, wherein the generating step comprises:

determining a correspondence relation between the extracted context topic keywords and each of the identified interactive operation users; and

generating one or more topic keywords by using the determined correspondence relation.

4. The method according to claim 1, wherein said messages having replying or forwarding relationship with the selected message comprise at least one of:

messages replying to or forwarding the selected message;

messages with respect to which the selected message replies or forwards; and

messages replying to or forwarding the messages with respect to which the selected message replies or forwards.

5. The method according to claim 1, further comprising, for each of the plurality of users:

determining a user level of the user;

comparing the determined user level with a preset level threshold; and

if the user level of the user is higher than the preset level threshold, identifying the user as an interactive operation user associated with the selected message.

6. The method according to claim 1 wherein

the extracting, generating and grouping steps comprise:

extracting, from the selected message, one or more first kernel topic keywords, and extracting, from the identified first context messages, one or more first context topic keywords;

generating one or more first topic keywords by combining the extracted first kernel topic keywords and the extracted first context topic keywords;

obtaining a first topic grouping result with respect to the selected message on the basis of the generated first topic keywords;

extracting one or more second context topic keywords from the identified second context messages by making reference to a correspondence relation between the identified second context messages and each of the identified interactive operation users;

obtaining a second topic grouping result with respect to the selected message on the basis of the extracted second context topic keywords; and

generating a combined topic grouping result by combining and analyzing the first topic grouping result and the second topic grouping result.

7. An apparatus for tracking message topics in an interactive messaging environment, wherein the interactive messaging environment contains a plurality of messages, the apparatus comprising:

a processor;

a memory;

message selecting means configured to select a message from the plurality of messages contained in the interactive messaging environment;

context message identifying means configured to;

determine a predetermined topic field of topics to be tracked;

for each of a plurality of users;

acquire topic preferences of the user by analyzing interactive operations of the user in the interactive messaging environment;

compare the acquired topic preferences of the user with the determined predetermined topic field; and

identify the user as an interactive operation user associated with the selected message if the topic preferences of the user match the predetermined topic field; and

identify, from messages corresponding to each of one or more identified interactive operation users, messages having replying or forwarding relations with the selected message, as context messages associated with the message selected by the message selecting means; and

grouping means configured to;

extract one or more context topic keywords from the identified context messages;

generate one or more topic keywords by processing the extracted context topic keywords; and

group the selected message into one or more topic groups corresponding to the generated one or more topic keyword respectively.

8. The apparatus according to claim 7, wherein the grouping means are further configured to

extract, from the selected message, one or more kernel topic keywords;

and

generate one or more topic keywords by combining the extracted kernel topic keywords and the extracted context topic keywords.

9. The apparatus according to claim 7, wherein the grouping means are configured to generate one or more topic keywords by:

determining a correspondence relation between the extracted context topic keywords and each of the identified interactive operation users; and

generating one or more topic keywords by using the determined correspondence relation.

10. The apparatus according to claim 7, wherein the messages having replying or forwarding relations with the selected message comprises at least one of:

messages replying to or forwarding the selected message;

messages with respect to which the selected message replies or forwards; and

messages replying to or forwarding the messages with respect to which the selected message replies or forwards.

11. The apparatus according to claim 7, wherein the context message identifying means are further configured to:

determine a user level of the user;

compare the determined user level with a preset level threshold; and

identify the user as an interactive operation user associated with the selected message if the user level of the user is higher than the preset level threshold.

12. The apparatus according to claim 7, wherein,

the grouping means are configured to:

extract, from the selected message, one or more first kernel topic keywords and to extract, from the identified first context messages, one or more first context topic keywords;

generate one or more first topic keywords by combining the extracted first kernel topic keywords and the extracted first context topic keywords;

obtain a first topic grouping result with respect to the selected message on the basis of the generated first topic keywords;

extract one or more second context topic keywords from the identified second context messages by making reference to a correspondence relation between the identified second context messages and the interactive operation user;

obtain a second topic grouping result with respect to the selected message on the basis of the extracted second context topic keywords; and

generate a combined topic grouping result by combining and analyzing the first topic grouping result and the second topic grouping result.