Communication processing
View Patent ↗Disclosed are methods and apparatus for processing linguistic expressions (e.g., opinionated text documents). The linguistic expressions are processed by, firstly, detecting topics of interest discussed in the linguistic expressions. The sentiment, or sentiments, of an originator with respect to each of the topics detected in the linguistic expressions is then assessed. The originators are then grouped (or clustered) into one or more groups based on the similarities between the originators' respective sets of detected topics and corresponding sentiments. Semantic information is then associated with a given group. Finally, for a given member of a given group, a profile is created or updated. This profile comprises attributes that may be based on a degree of membership of the given member to the given group and the semantic information associated with the given group.
1. A method of processing a plurality of linguistic expressions, each linguistic expression originating from an originator, and each linguistic expression being a linguistic expression in which the originator of that linguistic expression expresses a respective sentiment with respect to one or more topics, the method comprising:
for each linguistic expression, detecting, by one or more processors, one or more topics of interest addressed in that linguistic expression by the originator of that linguistic expression;
for each linguistic expression, for each topic detected in that linguistic expression, assessing, by the one or more processors, a sentiment of the originator of that linguistic expression with respect to that topic;
grouping, by the one or more processors, the originators into one or more groups based on similarities between the originators' respective sets of detected topic-sentiment pairs;
associating with a given group, by the one or more processors, semantic information, wherein the semantic information associated with the given group relates to one or more features selected from a group of features consisting of:
properties of one or more members of that given group and the sets of topic-sentiment pairs of one or more of the members of that given group; and
for a given originator, creating or updating, by the one or more processors, a profile;
wherein the given originator is a member of the given group;
wherein the profile is created or updated such that it comprises attributes of the given originator; and
wherein the attributes are dependent upon the given originator's membership in the given group and the semantic information associated with the given group.
2. A method according to claim 1 :
wherein each originator is a user of a network;
wherein each linguistic expression is made available on the network, by its originator, to other users of the network; and
wherein the network is selected from a group consisting of: the Internet, an intranet, a social network, and an online forum.
3. A method according to claim 1 further comprising:
receiving, by the one or more processors, categorization information corresponding to one or more of the members of the given group;
wherein the semantic information that is associated with the given group comprises some or all of the received categorization information.
4. A method according to claim 1 wherein associating the semantic information with the given group comprises using knowledge of a given topic and knowledge of a predominant sentiment with respect to that given topic of the members of the given group.
5. A method according to claim 1 further comprising:
for one or more of the groups of which the given originator is a member, determining, by the one or more processors, a respective membership value, the respective membership value being dependent on the degree of affiliation of the given originator with a respective group; and
including, by the one or more processors, in the profile of a second originator, the one or more membership values.
6. A method according to claim 1 wherein one or more of the linguistic expressions are text documents.
7. A method according to claim 1 further comprising:
delivering, by the one or more processors, for interaction with a second originator, data depending on the profile of the second originator.
8. Apparatus for processing a plurality of linguistic expressions, each linguistic expression originating from an originator, and each linguistic expression being a linguistic expression in which the originator of that linguistic expression expresses a respective sentiment with respect to one or more topics, the apparatus comprising one or more processors configured to:
for each linguistic expression, detect one or more topics of interest addressed in that linguistic expression by the originator of that linguistic expression;
for each linguistic expression, for each topic detected in that linguistic expression, assess a sentiment of the originator of that linguistic expression with respect to that topic;
group the originators into one or more groups based on similarities between the originators' respective sets of detected topic-sentiment pairs;
associate, with a given group, semantic information, wherein the semantic information associated with the given group relates to one or more feature selected from a group of features consisting of: properties of one or more members of that given group and the sets of topic-sentiment pairs of one or more of the members of that given group; and
for a given originator, create or update a profile;
wherein the given originator is a member of the given group;
wherein the profile is created or updated such that it comprises attributes of the given originator; and
wherein the attributes are dependent upon the given originator's membership in the given group and the semantic information associated with the given group.
9. Apparatus according to claim 8 :
wherein each originator is a user of a network;
wherein each linguistic expression is made available on the network, by its originator, to other users of the network; and
wherein the network is selected from a group consisting of: the Internet, an intranet, a social network, and an online forum.
10. Apparatus according to claim 8 :
wherein the one or more processors are further configured to receive categorization information corresponding to one or more of the members of the given group; and
wherein the semantic information that is associated with the given group comprises some or all of the received categorization information.
11. Apparatus according to claim 8 wherein associating the semantic information with the given group comprises using knowledge of a given topic and knowledge of a predominant sentiment with respect to that given topic of the members of the given group.
12. Apparatus according to claim 8 wherein the one or more processors are further configured to:
for one or more of the groups of which the given originator is a member, determine a respective membership value, the respective membership value being dependent on the degree of affiliation of the given originator with a respective group; and
include in the profile of a second originator, the one or more membership values.
13. Apparatus according to claim 8 wherein one or more of the linguistic expressions are text documents.
14. Apparatus according to claim 8 wherein the one or more processors are further configured to deliver, for interaction with a second originator, data depending on the profile of the second originator.