DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis

@inproceedings{Baziotis2017DataStoriesAS,
  title={DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis},
  author={Christos Baziotis and Nikos Pelekis and Christos Doulkeridis},
  booktitle={SemEval@ACL},
  year={2017}
}
In this paper we present two deep-learning systems that competed at SemEval-2017 Task 4 “Sentiment Analysis in Twitter”. We participated in all subtasks for English tweets, involving message-level and topic-based sentiment polarity classification and quantification. We use Long Short-Term Memory (LSTM) networks augmented with two kinds of attention mechanisms, on top of word embeddings pre-trained on a big collection of Twitter messages. Also, we present a text processing tool suitable for… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS
24 Citations
36 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 36 references

Sentiment Symposium Tutorial: Tokenizing

  • Christopher Potts.
  • http: //sentiment.christopherpotts.net…
  • 2011
Highly Influential
9 Excerpts

SemEval-2017 Task 4: Sentiment Analysis in Twitter

  • Sara Rosenthal, Noura Farra, Preslav Nakov.
  • Proceedings of SemEval. Vancouver, Canada.
  • 2017
2 Excerpts

Similar Papers

Loading similar papers…