Title
Unsupervised method for sentiment analysis in online texts.
Abstract
•Method to predict sentiment in informal texts using unsupervised dependency parsing.•Algorithm based on sentiment propagation using linguistic content without training.•Method to create lexicon using polarity expansion algorithm for specific domains.•Our method compares favorably well with other unsupervised and supervised methods.
Year
DOI
Venue
2016
10.1016/j.eswa.2016.03.031
Expert Systems with Applications
Keywords
Field
DocType
Sentiment analysis,Opinion mining,nlp,Artificial intelligence
Data mining,Social network,Computer science,Sentiment analysis,Dependency grammar,Robustness (computer science),Lexicon,Artificial intelligence,Natural language processing,Digital media,Machine learning
Journal
Volume
Issue
ISSN
58
C
0957-4174
Citations 
PageRank 
References 
30
0.91
58
Authors
5