This paper describes our proposal for Sentiment Analysis in Twitter for the Spanish language. The main characteristics of the system are the use of word embedding specifically trained from tweets in Spanish and the use of self-attention mechanisms that allow to consider sequences without using convolutional nor recurrent layers. These self-attention mechanisms are based on the encoders of the Transformer model. The results obtained on the Task 1 of the TASS 2019 workshop, for all the Spanish variants proposed, support the correctness and adequacy of our proposal.
AmbartsoumianA. and PopowichF., Self-attention: A better building block for sentiment analysis neural network classifiers. In WASSA@EMNLP, (2018).
2.
BaL.J., KirosR. and HintonG.E., Layer normalization, CoRR, abs/1607.06450, (2016).
3.
BirdS., KleinE. and LoperE., Natural Language Processing with Python. O’Reilly Media, (2009).
4.
CámaraE.M., Almeida-CruzY., Díaz-GalianoM.C., Estévez-VelardeS., CumbrerasM.Á.G., VegaM.G., GutiérrezY., Montejo-RáezA., MontoyoA., MuñozR., Piad-MorffisA. and Villena-RománJ., Overview of TASS 2018: Opinions, health and emotions. In Proceedings of TASS 2018: Workshop on Semantic Analysis at SEPLN, TASS@SEPLN 2018, co-located with 34nd SEPLN Conference (SEPLN 2018), Sevilla, Spain, September 18th, 2018., pages 13–27, (2018).
5.
ChiruzzoL. and RosáA., Retuyt-inco at TASS 2018: Sentiment analysis in spanish variants using neural networks and SVM. In Proceedings of TASS 2018:Workshop on Semantic Analysis at SEPLN, TASS@SEPLN 2018, co-located with 34nd SEPLN Conference (SEPLN 2018), Sevilla, Spain, September 18th, 2018., pages 57–63, (2018).
6.
Díaz-GalianoM.C., et al., Overview of TASS 2019. Bilbao, Spain, (2019). CEUR-WS.
7.
García CumbrerasM.Á., Villena RománJ., Martínez CámaraE., Díaz GalianoM.C., Martín ValdiviaM.T. and Ureña LópezL.A., Overview of TASS 2016. In Proceedings of TASS 2016: Workshop on Sentiment Analysis at SEPLN colocated with 32nd SEPLN Conference (SEPLN 2016), Salamanca, Spain, September 13th, 2016., pages 13–21, (2016).
8.
GonzálezJ., PlaF. and HurtadoL., Elirf-upv en TASS 2018: Análisis de sentimientos en twitter basado en aprendizaje profundo (elirf-upv atTASS 2018: Sentiment analysis in twitter based on deep learning). In Proceedings of TASS 2018: Workshop on Semantic Analysis at SEPLN, TASS@SEPLN 2018, colocated with 34nd SEPLN Conference (SEPLN 2018), Sevilla, Spain, September 18th, 2018., pages 37–44, (2018).
9.
GraffM., TellezE.S., Miranda-JiménezS. and EscalanteH.J., EvoDAG: A semantic Genetic Programming Python library. In 2016 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), pages 1–6, Nov. (2016).
10.
HochreiterS. and SchmidhuberJ., Long short-term memory, Neural Comput9(8) (1997), 1735–1780.
11.
IyyerM., ManjunathaV., Boyd-GraberJ. and DauméH., III, Deep unordered composition rivals syntactic methods for text classification, In Proceedings of the 53rd Annual Meeting of the Association forComputational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1681–1691, Beijing, China, July (2015). Association for Computational Linguistics.
12.
LetarteG., ParadisF., GiguèreP. and LavioletteF., Importance of self-attention for sentiment analysis, In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 267–275, Brussels, Belgium, Nov. (2018). Association for Computational Linguistics.
13.
LiuB., HuM. and ChengJ., Opinion Observer: Analyzing and Comparing Opinions on theWeb, In Proceedings of the 14th International Conference on WorldWideWeb, WWW’05, pages 342–351, New York, NY, USA, 2005. ACM.
14.
Martínez-CámaraE., Díaz-GalianoM.C., García-CumbrerasM.A., García-VegaM. and Villena-RománJ., Overview of TASS 2017. In J. Villena Román, M.A. García Cumbreras, E. Martínez-Cámara, M.C. Díaz Galiano and M. García Vega, editors, Proceedings of TASS 2017: Workshop on Semantic Analysis at SEPLN (TASS 2017), CEUR Workshop Proceedings, pages 13–21, Murcia, Spain, September (2017). CEUR-WS.
15.
Martínez-CámaraE., Martín-ValdiviaM.T., Molina-GonzálezM.D. and Ureña-LópezL.A., Bilingual Experiments on an Opinion Comparable Corpus, In Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, (2013), page 87–93.
16.
MikolovT., SutskeverI., ChenK., CorradoG. and DeanJ., Distributed representations of words and phrases and their compositionality, In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, NIPS’13, pages 3111–3119, USA, (2013). Curran Associates Inc.
17.
MoctezumaD., Ortiz-BejarJ., TellezE.S., Miranda-JiménezS. and GraffM., INGEOTEC solution for task 1 in tass’18 competition. In Proceedings of TASS 2018: Workshop on Semantic Analysis at SEPLN, TASS@SEPLN 2018, colocated with 34nd SEPLN Conference (SEPLN 2018), Sevilla, Spain, September 18th, 2018., pages 45–49, (2018).
18.
NakovP., RitterA., RosenthalS., SebastianiF. and StoyanovV., SemEval-2016 task 4: Sentiment analysis in twitter. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 1–18, San Diego, California, June (2016). Association for Computational Linguistics.
19.
Perez-RosasV., BaneaC. and MihalceaR., Learning Sentiment Lexicons in Spanish. (In N. C. C. Chair), K. Choukri, T. Declerck, M.U. Doğan, B. Maegaard, J. Mariani, J. Odijk and S. Piperidis, editors, Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey, may (2012). European Language Resources Association (ELRA).
20.
RosenthalS., FarraN. and NakovP., SemEval-2017 task 4: Sentiment analysis in twitter, In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 502–518, Vancouver, Canada, Aug. (2017). Association for Computational Linguistics.
21.
SaralegiX. and San VicenteI., Elhuyar at TASS 2013, In Proceedings of the TASS workshop at SEPLN 2013, IV Congreso Español de Informática, (2013).
22.
SocherR., PerelyginA., WuJ., ChuangJ., ManningC.D., NgA. and PottsC., Recursive deep models for semantic compositionality over a sentiment treebank, In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631–1642, Seattle,Washington, USA, Oct. (2013). Association for Computational Linguistics.
23.
SrivastavaN., HintonG., KrizhevskyA., SutskeverI. and SalakhutdinovR., Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research15 (2014), 1929–1958.
24.
TellezE.S., Miranda-JiménezS., GraffM., MoctezumaD., SuárezR.R. and SiordiaO.S., A Simple Approach to Multilingual Polarity Classification in Twitter, Pattern Recognition Letters, (2017).
25.
UryupinaO., PlankB., SeverynA., RotondiA. and MoschittiA., SenTube: Acorpus for sentiment analysis onYouTube social media, In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 4244–4249, Reykjavik, Iceland, May 2014. European Language Resources Association (ELRA).
26.
VaswaniA., ShazeerN., ParmarN., UszkoreitJ., JonesL., GomezA.N., KaiserL.U. and PolosukhinI., Attention is all you need. In I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan and R. Garnett, editors, Advances in Neural Information Processing Systems30 pages 5998–6008. Curran Associates, Inc., (2017).
27.
Villena-RománJ., García MoreraJ., García CumbrerasM.Á., Martínez CámaraE., Martín ValdiviaM.T. and Ureña LópezL.A., Workshop on Sentiment Analysis at SEPLN 2013: An overview, In Proceedings of the TASS workshop at SEPLN 2013. Villena-Román, Julio; García Morera, Janine; García Cumbreras, Miguel Ángel; Martínez Cámara, Eugenio; Martín Valdivia, M. Teresa; Ureña López, L. Alfonso, (2013).
28.
Villena-RománJ., García MoreraJ., García CumbrerasM.Á., Martínez CámaraE., Martín ValdiviaM.T. and Ureña LópezL.A., Workshop on Sentiment Analysis at SEPLN: Overview, In Proceedings of the TASS workshop at SEPLN 2014. Villena-Román, Julio; García Morera, Janine; García Cumbreras, Miguel Ángel; Martínez Cámara, Eugenio; Martín Valdivia, M. Teresa; Ureña López, L. Alfonso, (2014).
29.
Villena-RománJ., García MoreraJ., García CumbrerasM.Á., Martínez CámaraE., Martín ValdiviaM.T. and Ureña LópezL.A., Overview of TASS 2015. In TASS 2015: Workshop on Sentiment Analysis at SEPLN co-located with 31st SEPLN Conference (SEPLN 2015). http://ceur-ws.org/Vol-1397/, pages 13–21. Villena-Román, Julio; García Morera, Janine; García Cumbreras, Miguel Ángel; Martínez Cámara, Eugenio; Martín Valdivia, M. Teresa; Ureña López, L. Alfonso, (2015).
30.
WilsonT., HoffmannP., SomasundaranS., KesslerJ., WiebeJ., ChoiY., CardieC., RiloffE. and PatwardhanS., Opinion-Finder: A system for subjectivity analysis, In Proceedings of HLT/EMNLP on Interactive Demonstrations, pages 34–35. Association for Computational Linguistics, (2005).
