MAPPING SOCIAL MEDIA SENTIMENTS

• US 20170352070A1
• Filed: 08/16/2017
• Published: 12/07/2017
• Est. Priority Date: 06/07/2016
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DeLuca, Lisa Seacat, Greenberger, Jeremy A.
• Application Number:
  US15/678,244
• Publication Number:
  US 20170352070A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/41 Interactive pattern learning with a human teacher
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A computer-implemented method includes accessing social media data, wherein the social media data is associated with one or more profiles and corresponds to a venue. The computer-implemented method further includes determining sentiment information corresponding to each of the one or more profiles based on the social media data. The computer-implemented method further includes, for each of the one or more profiles: identifying a path through the venue, wherein the path represents at least one movement associated with the profile and associating the sentiment information with the path through the venue. The computer-implemented method further includes, responsive to associating the sentiment information with the path through the venue for each of the one or more profiles, identifying one or more trends. The computer-implemented method further includes presenting the one or more trends for review. A corresponding computer system and computer program product are also disclosed.

Claims

1. A computer-implemented method comprising:

accessing social media data, said social media data being associated with one or more profiles and corresponding to a venue;

determining sentiment information corresponding to social media data associated with each of said one or more profiles, wherein said sentiment information is determined based, at least in part, on;

a visual sentiment ontology;

an image data set corresponding to said visual sentiment ontology; and

supervised machine learning;

determining that a facial expression of a user of a mobile device matches said determined sentiment information at the time said user of said mobile device generated said social media data;

for each of said one or more profiles;

identifying a path through said venue, said path representing at least one movement associated with said profile;

associating said sentiment information with said path through said venue, wherein associating said sentiment information with said path through said venue comprises;

mapping one or more instances of said sentiment information to one or more corresponding areas of said venue along said path through said venue; and

generating a sentiment map based on said mapping, wherein said sentiment map displays one or more details of said social media data;

responsive to associating said sentiment information with said path through said venue for each of said one or more profiles;

identifying one or more trends; and

presenting said one or more trends for review, wherein presenting said one or more trends for review comprises;

generating one or more corrective suggestions corresponding to each of said one or more trends; and

generating a response to said social media data based on said mapping of said one or more instances of said sentiment information to one or more corresponding areas of said venue along said path through said venue.