Advertisement

A Comparative Evaluation of Preprocessing Techniques for Short Texts in Spanish

  • Marcos Orellana
  • Andrea Trujillo
  • Priscila CedilloEmail author
Conference paper
  • 24 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1130)

Abstract

Natural Language Processing (NLP) is used to identify key information, generating predictive models, and explaining global events or trends. Also, NLP is supported during the process to create knowledge. Therefore, it is important to apply refinement techniques in major stages such as preprocessing, when data is frequently produced and processed with poor results. This document analyzes and measures the impact of combinations of preprocessing techniques and libraries for short texts that have been written in Spanish. These techniques were applied in tweets for analysis of sentiments considering evaluation parameters in its analysis, the processing time and characteristics of the techniques for each library. The performed experimentation provides readers insights for choosing the appropriate combination of techniques during preprocessing. The results show improvement of up to 5% to 9% in the performance of the classification.

Keywords

Natural Language Processing Preprocessing Twitter Sentiment analysis Text mining 

Notes

Acknowledgment

This research was supported by the vice-rectorate of investigations of the Universidad del Azuay. We thank our colleagues from Laboratorio de Investigación y Desarrollo en Informática (LIDI) at Universidad del Azuay who provided insight and expertise that greatly assisted this work. Part of this research is supported by the Design of architectures and interaction models for assisted living environments aimed at older adults project of the XVIII DIUC Call for Research.

References

  1. 1.
    Reese, R.M.: Natural Language Processing with Java. Packt Publishing (2015)Google Scholar
  2. 2.
    Battistelli, D., Charnois, T., Minel, J.L., Teissèdre, C.: Detecting salient events in large corpora by a combination of NLP and data mining techniques. Comput. y Sist. 17, 229–237 (2013)Google Scholar
  3. 3.
    Uysal, A.K., Gunal, S.: The impact of preprocessing on text classification. Inf. Process. Manage. 50, 104–112 (2014).  https://doi.org/10.1016/j.ipm.2013.08.006CrossRefGoogle Scholar
  4. 4.
    Krouska, A., Troussas, C., Virvou, M.: The effect of preprocessing techniques on twitter sentiment analysis. In: 2016 7th International Conference on Information, Intelligent System Application (IISA), pp. 1–5 (2016).  https://doi.org/10.1109/iisa.2016.7785373
  5. 5.
    Hidalgo, O., Jaimes, R., Gomez, E., Luján-mora, S.: Análisis de sentimiento aplicado al nivel de popularidad del líder político ecuatoriano Rafael Correa Sentiment Analysis applied to the popularity level of the Ecuadorian political leader Rafael Correa. In: 2017 International Conference on Information Systems and Computer Science (INCISCOS), pp. 340–346 (2017)Google Scholar
  6. 6.
    Gómez-Jiménez, G., Gonzalez-Ponce, K., Castillo-Pazos, D.J., Madariaga-Mazon, A., Barroso-Flores, J., Cortes-Guzman, F., Martinez-Mayorga, K.: The OECD Principles for (Q)SAR Models in the Context of Knowledge Discovery in Databases (KDD). Elsevier Inc. (2018)Google Scholar
  7. 7.
    Haddi, E., Liu, X., Shi, Y.: The role of text pre-processing in sentiment analysis. Procedia Comput. Sci. 17, 26–32 (2013).  https://doi.org/10.1016/j.procs.2013.05.005CrossRefGoogle Scholar
  8. 8.
    Gupta, I., Joshi, N.: Tweet normalization : a knowledge based approach. In: 2017 International Conference on Infocom Technologies and Unmanned Systems (Trends Future Directions) (ICTUS), pp. 1–6 (2017)Google Scholar
  9. 9.
    Jianqiang, Z., Xiaolin, G.: Comparison research on text pre-processing methods on twitter sentiment analysis. IEEE Access. 5, 2870–2879 (2017).  https://doi.org/10.1109/ACCESS.2017.2672677CrossRefGoogle Scholar
  10. 10.
    Galadanci, B.S., Muaz, S.A., Mukhtar, M.I.: Comparing research outputs of Nigeria Federal Universities based on the scopus database. In: CEUR Workshop Proceedings, vol. 1755, pp. 79–84 (2016).  https://doi.org/10.1177/0165551510000000
  11. 11.
    Paramkusham, S.: NLTK: The natural language toolkit. Int. J. Technol. Res. Eng. 5, 2845–2847 (2017)Google Scholar
  12. 12.
    Weerasooriya, T., Perera, N., Liyanage, S.R.: A method to extract essential keywords from a tweet using NLP tools. In: 16th International Conference on Advances in ICT for Emerging Regions, ICTer 2016 - Conference Proceedings, pp. 29–34 (2017)Google Scholar
  13. 13.
  14. 14.
    Padró, L., Stanilovsky, E.: FreeLing 3.0: towards wider multilinguality. In: Proceedings Language Resources Evaluation Conference (LREC 2012), pp. 2473–2479 (2012)Google Scholar
  15. 15.
    Henríquez, C., Guzmán, J., Salcedo, D.: Minería de Opiniones basado en la adaptación al español de ANEW sobre opiniones acerca de hoteles. Proces. del Leng. Nat. 41, 25–32 (2016)Google Scholar
  16. 16.
    Prata, D.N., Soares, K.P., Silva, M.A., Trevisan, D.Q., Letouze, P.: Social data analysis of Brazilian’s mood from twitter. Int. J. Soc. Sci. Humanit. 6, 179–183 (2016).  https://doi.org/10.7763/IJSSH.2016.V6.640CrossRefGoogle Scholar
  17. 17.
    Altszyler, E., Brusco, P.: Análisis de la dinámica del contenido semántico de textos. In: Argentine Symposium on Artificial Intelligence, pp. 256–263 (2015)Google Scholar
  18. 18.
    Pérez-guadarramas, Y., Rodríguez-blanco, A., Simón-cuevas, A.: Combinando patrones léxico - sintácticos y análisis de tópicos para la extracción automática de frases relevantes en textos. Proces. L. 59, 39–46 (2017)Google Scholar
  19. 19.
    Antonio, F., Velásquez, C., Paul, J., De Paz, Z., Guzmán, J.F.: Aplicación del análisis sintáctico automático en la atribución de autoría de mensajes en redes sociales. Res. Comput. Sci. 137, 109–119 (2017)Google Scholar
  20. 20.
    Soto Kiewit, L.D.: Un acercamiento a la concepción de gobernabilidad en los discursos presidenciales de José María Figueres Olsen. Rev. Rupturas. 7, 1 (2017).  https://doi.org/10.22458/rr.v7i1.1609CrossRefGoogle Scholar
  21. 21.
    Poornima, B.K.: Text preprocessing on extracted text from audio/video using R. Int. J. Comput. Intell. Inform. 6, 267–278 (2017)Google Scholar
  22. 22.
    He, Y., Kayaalp, M.: A comparison of 13 tokenizers on MEDLINE. Bethesda, MD List. Hill Natl. Cent. Biomed. Commun. 48 (2006)Google Scholar
  23. 23.
    Alami, N., Meknassi, M., Ouatik, S.A., Ennahnahi, N.: Impact of stemming on Arabic text summarization. In: Colloquium in Information Science and Technology, CIST, pp. 338–343 (2017)Google Scholar
  24. 24.
    Singh, T., Kumari, M.: Role of text pre-processing in twitter sentiment analysis. Procedia Comput. Sci. 89, 549–554 (2016).  https://doi.org/10.1016/j.procs.2016.06.095CrossRefGoogle Scholar
  25. 25.
    Katariya, N.P., Chaudhari, M.S.: Text preprocessing for text mining using side information. Int. J. Comput. Sci. Mob. Appl. 3, 3–7 (2015)Google Scholar
  26. 26.
    Althobaiti, M., Kruschwitz, U., Poesio, M.: AraNLP: a Java-based library for the processing of Arabic text. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 4134–4138 (2014)Google Scholar
  27. 27.
  28. 28.
    RStudio: Take control of your R code. https://www.rstudio.com/products/rstudio/
  29. 29.
    GmbH R: Rapidminer DocumentationGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Universidad del AzuayCuencaEcuador
  2. 2.Universidad de CuencaCuencaEcuador

Personalised recommendations