Twitter’s Experts Recommendation System Based on User Content

  • Diego M. Jiménez-BravoEmail author
  • Juan F. De Paz
  • Gabriel Villarrubia
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 801)


The Internet provides users with an overwhelming amount of information. For this reason they may not always be able to find the information they are looking for. Recommendation systems help users locate useful information and save time. Twitter is one of the social networks that implements this type of system in order to help its users in searching content. However, the traditional recommendation system implemented by Twitter only considers people from the user’s surroundings or it suggests the followees/followers of the user’s followees. Many use Twitter as a source of information, it is therefore necessary to create a recommendation system that would suggest experts profiles to other users. Experts must be capable of providing interesting information to users. The “expert” recommended to a users will be chosen on the basis of the content they publish and whether this content is of interest to the user. The proposed system offers accurate and suitable recommendations.


Content-based recommendation Information retrieval Recommendation system Text mining Twitter Web mining 



This work has been supported by project MOVIURBAN: Máquina social para la gestión sostenible de ciudades inteligentes: movilidad urbana, datos abiertos, sensores móviles. SA070U 16. Project co-financed with Junta Castilla y León, Consejería de Educación and FEDER funds.


  1. 1.
    Kywe, S.M., Lim, E.P., Zhu, F.: A survey of recommender systems in Twitter, vol. 7710, pp. 420–433 (2012)Google Scholar
  2. 2.
    Su, X., Khoshgoftaar, T.M.: A survey of collaborative filtering techniques. Adv. Artif. Intell. 2009, 1–19 (2009)CrossRefGoogle Scholar
  3. 3.
    Jalili, M.: A survey of collaborative filtering recommender algorithms and their evaluation metrics. Int. J. Syst. Model. Simul. 2(2), 14 (2017)Google Scholar
  4. 4.
    Armentano, M.G., Godoy, D.L., Amandi, A.A.: A topology-based approach for followees recommendation in Twitter (2011)Google Scholar
  5. 5.
    Hannon, J., McCarthy, K., Smyth, B.: Finding useful users on Twitter: Twittomender the followee recommender, pp. 784–787. Springer, Heidelberg (2011)Google Scholar
  6. 6.
    Garcia, R., Amatriain, X.: Weighted content based methods for recommending connections in online social networks, pp. 68–71 (2010)Google Scholar
  7. 7.
    Golder, S.A., Yardi, S., Marwick, A., Boyd, D.: A Structural Approach to Contact Recommendations in Online Social Networks (2009)Google Scholar
  8. 8.
    Elmongui, H.G., Mansour, R., Morsy, H., Khater, S., El-Sharkasy, A., Ibrahim, R.: TRUPI: Twitter Recommendation Basedon Users’ Personal Interests, pp. 272–284. Springer, Cham (2015)Google Scholar
  9. 9.
    Shouzhong, T., Minlie, H.: Mining microblog user interests based on textrank with TF-IDF factor. J. China Univ. Posts Telecommun. 23(5), 40–46 (2016)CrossRefGoogle Scholar
  10. 10.
    Trstenjak, B., Mikac, S., Donko, D.: KNN with TF-IDF based framework for text categorization. Procedia Eng. 69, 1356–1364 (2014)CrossRefGoogle Scholar
  11. 11.
    Aizawa, A.: An information-theoretic perspective of tf-idf measures. Inf. Process. Manag. 39(1), 45–65 (2003)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Visual Workflow Designer for Data Scientists — RapidMiner Studio — RapidMiner (2008)Google Scholar
  13. 13.
    Huang, J., Ling, C.X.: Using AUC and accuracy in evaluating learning algorithms. IEEE Trans. Knowl. Data Eng. 17(3), 299–310 (2005)CrossRefGoogle Scholar
  14. 14.
    Lobo, J.M., Jiménez-valverde, A., Real, R.: AUC: a misleading measure of the performance of predictive distribution models. Glob. Ecol. Biogeogr. 17(2), 145–151 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Diego M. Jiménez-Bravo
    • 1
    Email author
  • Juan F. De Paz
    • 1
  • Gabriel Villarrubia
    • 1
  1. 1.BISITE Digital Innovation HubUniversity of SalamancaSalamancaSpain

Personalised recommendations