FINKI at semeval-2016 task 4: Deep learning architecture for twitter sentiment analysis
Date Issued
2016-06
Author(s)
Stojanovski, Dario
Strezoski, Gjorgji
Madjarov, Gjorgji
Abstract
In this paper, we present a novel deep learning
architecture for sentiment analysis in Twitter
messages. Our system finki, employs both
convolutional and gated recurrent neural networks to obtain a more diverse tweet representation. The network is trained on top of
GloVe word embeddings pre-trained on the
Common Crawl dataset. Both neural networks are used to obtain a fixed length representation of variable sized tweets, and the
concatenation of these vectors is supplied to
a fully connected softmax layer with dropout
regularization. The system is evaluated on
benchmark datasets from the Sentiment Analysis in Twitter task of the SemEval 2016 challenge where our model achieves best and second highest results on the 2-point and 5-point
quantification subtasks respectively. Despite
not relying on any hand-crafted features, our
system manages the second highest average
rank on the considered subtasks.
architecture for sentiment analysis in Twitter
messages. Our system finki, employs both
convolutional and gated recurrent neural networks to obtain a more diverse tweet representation. The network is trained on top of
GloVe word embeddings pre-trained on the
Common Crawl dataset. Both neural networks are used to obtain a fixed length representation of variable sized tweets, and the
concatenation of these vectors is supplied to
a fully connected softmax layer with dropout
regularization. The system is evaluated on
benchmark datasets from the Sentiment Analysis in Twitter task of the SemEval 2016 challenge where our model achieves best and second highest results on the 2-point and 5-point
quantification subtasks respectively. Despite
not relying on any hand-crafted features, our
system manages the second highest average
rank on the considered subtasks.
File(s)![Thumbnail Image]()
Loading...
Name
S16-1022.pdf
Size
168.36 KB
Format
Adobe PDF
Checksum
(MD5):a336f9ec3e3feea8ec7da3aad7adab4b