Contextual Analysis of Comments in B2C Facebook Fan Pages Based on the Levenshtein Algorithm

  • Danny Jácome
  • Freddy TapiaEmail author
  • Jorge Edison Lascano
  • Walter Fuertes
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 918)


The present study proposes the implementation of an algorithm to determine the degree of reliability of Business to Consumer Facebook fan pages, to mitigate possible cheating, scams or fraud. We use data mining to filter information from comments expressed by online stores’ customers. The experiment determines a word dictionary to find matches using a Natural Language Processing technique. The main contribution of this research is the analysis of the context of online stores followers and customers that use Facebook as a business tool, this analysis is based on comments as opposed to the classic way of counting the number of likes. This analysis discards wrong and miswritten comments.


Social networks Facebook Data mining Business to Consumer Levenshtein algorithm Natural Language Processing 


  1. 1.
    INEC. Encuesta de Condiciones de vida realizada por el Instituto Nacional de Estadísticas y Censos. Quito (2014)Google Scholar
  2. 2.
    Ecommerce en Ecuador: Datos interesantes |, El Emprendedor, 05 July 2013Google Scholar
  3. 3.
    Haucap, J., Heimeshoff, U.: Google, Facebook, Amazon, eBay: is the internet driving competition or market monopolization? University of Düsseldorf, Düsseldorf Institute for Competition Economics (DICE), no. 83 (2013)Google Scholar
  4. 4.
    Overview - Graph API - Documentation, Facebook for Developers. Accessed 23 Sept 2018
  5. 5.
    Project Management Institute: Guía de los Fundamentos Para la Dirección de Proyectos, 5th edn. Project Management Institute (2014)Google Scholar
  6. 6.
    Virla, M.Q.: Confiabilidad y coeficiente Alpha de Cronbach, September 2018Google Scholar
  7. 7.
    Pruebas y evaluacion psicologicas: introduccion a las pruebas y a la medicion | ronald jay cohen | comprar libro 9789701057049. Accessed 23 Sept 2018
  8. 8.
    Mosley, R.: Social media analytics: data mining applied to insurance twitter posts. In: Casualty Actuarial Society E-Forum, Winter 2012, vol. 2 (2012)Google Scholar
  9. 9.
    Martel, W.: Determinación de niveles de agresividad en comentarios de la red social Facebook por medio de Minería de Texto (2016)Google Scholar
  10. 10.
    Bilenko, M., Mooney, R., Cohen, W., Ravikumar, P., Fienberg, S.: Adaptive name matching in information integration. IEEE Intell. Syst. 18(5), 16–23 (2003)CrossRefGoogle Scholar
  11. 11.
    Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A comparison of string distance metrics for name-matching tasks. In: Proceedings of the 2003 International Conference on Information Integration on the Web, Acapulco, Mexico, pp. 73–78 (2003)Google Scholar
  12. 12.
    Peng, T., Li, L., Kennedy, J.: A comparison of techniques for name matching. GSTF J. Comput. JoC 2(1), 55–61 (2018)Google Scholar
  13. 13.
    Miguélez, M.M.: Validez y confiabilidad en la metodología cualitativa. Paradigma 27(2), 7–33 (2016)Google Scholar
  14. 14.
    Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning and Object Consolidation, vol. 3, pp. 73–78 (2003)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Danny Jácome
    • 1
  • Freddy Tapia
    • 1
    Email author
  • Jorge Edison Lascano
    • 1
  • Walter Fuertes
    • 1
  1. 1.Universidad de las Fuerzas Armadas ESPESangolquíEcuador

Personalised recommendations