Sentiment classification of online political discussions: a comparison of a word-based and dependencybased method

Hammer, Hugo Lewi; Solberg, Per Erik; Øverlid, Lilja
Chapter, Peer reviewed
Creative commons attribution- non commercial- share alike 4.0 international license
Thumbnail
View/Open
URI
https://hdl.handle.net/10642/2321
Date
2014
Metadata
Show full item record
Collections
Original version
Hammer, H. L., Solberg, P. E., & Øvrelid, L. (2014). Sentiment classification of online political discussions: a comparison of a word-based and dependency-based method. Association for Computational Linguistics.   http://acl2014.org/acl2014/W14-26/pdf/W14-2616.pdf
Abstract
Online political discussions have received

a lot of attention over the past years. In

this paper we compare two sentiment lexicon

approaches to classify the sentiment of

sentences from political discussions. The

first approach is based on applying the

number of words between the target and

the sentiment words to weight the sentence

sentiment score. The second approach

is based on using the shortest paths

between target and sentiment words in a

dependency graph and linguistically motivated

syntactic patterns expressed as dependency

paths. The methods are tested

on a corpus of sentences from online Norwegian

political discussions. The results

show that the method based on dependency

graphs performs significantly better

than the word-based approach.
Publisher
Association for Computational Linguistics
Series
5th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis;