This repository contains the source code of a system that has competed in the Task 1 of the ESWC Challenge on Semantic Sentiment Analysis.
The approach is based on a Bidirectional LSTMs equipped with a neural attention mechanism.
More details are available in the following paper:
Atzeni M., Reforgiato Recupero D. (2018) Fine-Tuning of Word Embeddings for Semantic Sentiment Analysis. In: Buscaldi D., Gangemi A., Reforgiato Recupero D. (eds) Semantic Web Challenges. SemWebEval 2018. Communications in Computer and Information Science, vol 927. Springer, Cham, https://doi.org/10.1007/978-3-030-00072-1_12