Paper Info
Title
SentiBank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content
Abstract
A picture is worth one thousand words, but what words should be used to describe the sentiment and emotions conveyed in the increasingly popular social multimedia? We demonstrate a novel system which combines sound structures from psychology and the folksonomy extracted from social multimedia to develop a large visual sentiment ontology consisting of 1,200 concepts and associated classifiers called SentiBank. Each concept, defined as an Adjective Noun Pair (ANP), is made of an adjective strongly indicating emotions and a noun corresponding to objects or scenes that have a reasonable prospect of automatic detection. We believe such large-scale visual classifiers offer a powerful mid-level semantic representation enabling high-level sentiment analysis of social multimedia. We demonstrate novel applications made possible by SentiBank including live sentiment prediction of social media and visualization of visual content in a rich intuitive semantic space.
Year
DOI
Venue
2013
10.1145/2502081.2502268
ACM Multimedia 2001
Keywords
Field
DocType
large-scale ontology,popular social multimedia,high-level sentiment analysis,social media,novel system,live sentiment prediction,novel application,visual content,large-scale visual classifier,large visual sentiment ontology,social multimedia,affect,sentiment analysis,emotion,ontology
Ontology,Social media,Sentiment analysis,Computer science,Visualization,Noun,Folksonomy,Social multimedia,Artificial intelligence,Natural language processing,Multimedia,Adjective
Conference
Citations 
PageRank 
References 
53
1.26
3
Authors
4
Name
Order
Citations
PageRank
Damian Borth176449.45
Tao Chen259929.93
Rongrong Ji33616189.98
Shih-Fu Chang4130151101.53