UWB at SemEval-2016 Task 7: Novel Method for Automatic Sentiment Intensity Determination
Ladislav Lenc
and
Pavel Král
and
Václav Rajtmajer
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) (2016)
BibTex
|
PDF
Abstract
We present a novel method for determining
sentiment intensity. The main goal is to assign
a phrase a score from 0 to 1 which indicates
the strength of its association with positive
sentiment. The proposed model uses
a rich set of features with Gaussian processes
regression model that computes the final score. The system was evaluated on the
data from 7th task of SemEval 2016. Our
regression model trained on the development
data reached Kendall rank correlation of 0.659
on general English phrases and 0.414 on English
Twitter test data.