LyS at SemEval-2016 Task 4: Exploiting Neural Activation Values for Twitter Sentiment Classification and Quantification
Year: 2016
Type: conference-paper
Abstract: In this paper we describe our deep learning approach for solving both two-, three-and fiveclass tweet polarity classification, and twoand five-class quantification.We first trained a convolutional neural network using pretrained Twitter word embeddings, so that we could extract the hidden activation values from the hidden layers once some input had been fed to the network.These values were then used as features for a support vector machine in both the classification and quantification subtasks, together with additional linguistic information in the former scenario.The results obtained for the classification subtasks show that this approach performs better than a single convolutional network, and for the quantification part it also yields good results.Official rankings locate us: 2nd (practically tied with 1st) for the binary classification task, 2nd for binary quantification and 4th (practically tied with 3rd) for the five-class polarity classification challenge.
DOI: 10.18653/v1/s16-1009
Institutions: Universidade da Coruña, Universidade de Vigo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G2369381396, G5289862223, G8763453525
OpenAlex ID: W2469722296
