Predicting the success of online news about movies with Google Analytics and Twitter : A machine learning methodology

Yeste, Víctor; Calduch-Losa, Ángeles; Ontalba-Ruipérez, José Antonio; Serrano-Cobos, Jorge

doi:10.47974/JSMS-1379

Open Access Research Article

Predicting the success of online news about movies with Google Analytics and Twitter : A machine learning methodology

^*Víctor YesteCorresponding authorvicyesmo@upv.esAffiliation 1Department of Applied Statistics and Operational Research and QualityUniversitat Politècnica de ValènciaValencia, 46022, SpainAffiliation 2School of Science, Engineering and DesignUniversidad Europea de ValenciaValencia, 46010, Spain0000-0002-3660-8347View full profile → , Ángeles Calduch-Losamcalduch@eio.upv.esAffiliation 1Department of Applied Statistics and Operational Research and QualityUniversitat Politècnica de ValènciaValencia, 46022, SpainAffiliation 2Spain0000-0001-8287-7823View full profile → , José Antonio Ontalba-Ruipérezjoonrui@upv.esDepartment of Audiovisual Communication, Documentation and History of ArtUniversitat Politècnica de ValènciaValencia, 46022, Spain0000-0002-2071-6108View full profile → , Jorge Serrano-Cobosjorserc2@har.upv.esDepartment of Audiovisual Communication, Documentation and History of ArtUniversitat Politècnica de ValènciaValencia, 46022, Spain0000-0002-4394-4883View full profile →

* Corresponding author · click or hover a name for details

pp. 761–793Vol. 28Issue 4May 2025DOI: 10.47974/JSMS-1379XML

Received:: 05 Dec 2023
Published Online:: 12 May 2025
Article type:: Research Article
Language:: EN
Article no.:: JSMS-1379
Pages:: 761–793

Abstract

This paper presents a machine learning methodology for predicting the success of online movie news with web analytics data from Google Analytics and social media analytics data from Twitter (now known as X). This methodology is built in two phases. The first consists of segmenting the data with the different categories that apply to the articles (in this case, all news published, news about movies, and news with a trailer) and performing a multiple linear regression to extract a prediction equation for each success variable. The second phase includes validating the prediction equations with test data, which helps to select the most reliable prediction depending on its accuracy. This methodology has shown that it can account for some of the variability of the success variables and can make their prediction. It provides a basis for future research to improve accuracy and test new variables that can enrich this analysis. This article also helps editorial teams make better data-driven decisions, such as more efficient resource planning or optimising articles to achieve a specific goal.

Keywords

Online success Online news Digital journalism Web analytics Google Analytics Social media Social media analytics Twitter X Success prediction Multiple linear regression MLR Statistics Machine learning

Subject Classifications

62J0562P25

References

[1] W. Ahmed and S. Lugovic, “Social media analytics: analysis and visualisation of news diffusion using NodeXL”, Online Information Review, Vol. 43 No. 1, pp. 149-160 (2019). https://doi.org/10.1108/OIR-03-2018-0093.
[2] A. bin A. Al-Tameem and A. K. J. Saudagar, “Machine learning approach for identification of threat content in audio messages shared on social media”, Journal of Discrete Mathematical Sciences and Cryptography, Vol. 23 No. 1, pp. 83–93 (2020). https://doi.org/10.1080/09720529.2020.1721876.
[3] V. Álvarez Intriago, L. Agreda Fernández, and A. Cevallos Gamboa, “Análisis de la estrategia de marketing digital mediante herramientas de analítica web”, INVESTIGATIO, Vol. 7, pp. 81–97 (2016). https://doi.org/10.31095/IRR.V0I7.41.
[4] T. Araujo and J. Kollat, “Communicating effectively about CSR on Twitter: The power of engaging strategies and storytelling elements”, Internet Research, Vol. 28 No. 2, pp. 419-431 (2018). https://doi.org/10.1108/IntR-04-2017-0172.
[5] S. Asur, B. A. Huberman, G. Szabo, and C. Wang, “Trends in Social Media: Persistence and Decay”, SSRN Electronic Journal (2011). https://doi.org/10.2139/ssrn.1755748.
[6] F. J. Barón López and F. Téllez Montiel, “Apuntes de Bioestadística: Tercer Ciclo en Ciencias de la Salud y Medicina”, Apuntes de Bioestadística, Málaga (2004). https://www.bioestadistica.uma.es/baron/apuntes/ficheros/cap06.pdf.
[7] V. Belair-Gagnon and A. E. Holton, “Boundary Work, Interloper Media, And Analytics In Newsrooms: An analysis of the roles of web analytics companies in news production”, Digital Journalism, Vol. 6 No. 4, pp.492–508 (2018). https://doi.org/10.1080/21670811.2018.1445001.
[8] S. Bhoyar, P. Bhoyar, and M. A. Shah, A machine learning-based predictive approach in evaluating consumer behavior, Journal of Statistics and Management Systems, Vol. 26 No. 8, 1955–1963 (2023). https://doi.org/10.47974/JSMS-1131.
[9] Z. Bobbitt, “A Gentle Introduction to Poisson Regression for Count Data” (2019), available at: https://www.statology.org/poisson-regression/ (accessed 20 December 2020).
[10] R. M. Campos and C. G. Soares, “Comparison and assessment of three wave hindcasts in the North Atlantic Ocean”, Journal of Operational Oceanography, Vol. 9 No. 1, pp. 26–44 (2016). https://doi.org/10.1080/1755876X.2016.1200249.
[11] M. Carlson, “Confronting Measurable Journalism”, Digital Journalism, Vol. 6 No. 4, pp. 406–417 (2018). https://doi.org/10.1080/21670811.2018.1445003.
[12] C. Castillo, M. Mendoza, and B. Poblete, “Predicting information credibility in time-sensitive social media”, Internet Research, Vol. 23 No. 5, 560-588 (2013). https://doi.org/10.1108/IntR-05-2012-0095.
[13] M. Cristian, P. Morphl, and A. A. Morphl, “Predicting next shopping stage using Google Analytics data for E-commerce applications” (2019), unpublished manuscript, arXiv preprint, arXiv:1905.12595
[14] J. Díaz Noci, “Definición teórica de las características del ciberperiodismo: elementos de la comunicación digital”, Doxa Comunicación. Revista Interdisciplinar de Estudios de Comunicación y Ciencias Sociales, Vol. 6, pp. 53–91 (2008). https://doi.org/10.31921/doxacom.n6a2.
[15] e-intelligent.es., “Medir el éxito de nuestro Marketing de Contenidos (2014)”, available at: https://www.e-intelligent.es/es/blog/medir-el-exito-de-nuestro-marketing-de-contenidos (accessed 21 May 2019).
[16] S. Fox and A. Lenhart, “Twitter and status updating,” (2009). [Online]. Available: http://www.pewinternet.org/Reports/2009/Twitter-and. [Accessed: Jan. 11, 2020].
[17] S. Glen, “RMSE: Root Mean Square Error,” (2020). [Online]. Available: https://www.statisticshowto.com/probability-and-statistics/regression-analysis/rmse-root-mean-square-error/. [Accessed: Dec. 24, 2020].
[18] K. Grace-Martin, “Assessing the Fit of Regression Models - The Analysis Factor,” (2008). [Online]. Available: https://www.theanalysisfactor.
[19] A. Graefe, “Guide to Automated Journalism,” Tow Center for Digital Journalism (2016). [Online]. Available: https://doi.org/10.7916/D80G3XDJ.
[20] C. Gutiérrez Argüello, “Modelos de Comunicación y Negocios en Periódicos Digitales,” (2013). [Online]. Available: https://es.slideshare.net/CarlosGutArg/modelos-de-comunicacin-y-negocios-en-peridicosdigitales. [Accessed: May 6, 2019].
[21] A. Hermida, “Social Media and the News,” in The SAGE Handbook of Digital Journalism, SAGE Publications Ltd., London, pp. 81–94 (2016).
[22] L. Hong, O. Dan, and B. D. Davison, “Predicting Popular Messages in Twitter,” in Proceedings of the 20th International Conference Companion on World Wide Web, pp. 57-58 (2011). [Online]. Available: http://bit.ly/794Edz.
[23] J. Huang, Y. Tang, Y. Hu, J. Li, and C. Hu, “Predicting the active period of popularity evolution: A case study on Twitter hashtags”, Information Sciences, Vol. 512, pp.315–326 (2020). https://doi.org/10.1016/j.ins.2019.04.028.
[24] A. Java, X. Song, T. Finin, and B. Tseng, “Why We Twitter: An analysis of a microblogging community,” in International Workshop on Social Network Mining and Analysis, pp. 118-138 (2009). [Online]. Available: https://doi.org/10.1007/978-3-642-00528-2_7.
[25] V. Karnowski, D. J. Leiner, A. S. Kümpel, and L. Leonhard, “Worth to Share? How Content Characteristics and Article Competitiveness Influence News Sharing on Social Network Sites”, Journalism & Mass Communication Quarterly, Vol. 98 No. 1, pp. 59–82 (2021). https://doi.org/10.1177/1077699020940340.
[26] A. Kaushik, “Best Social Media Metrics: Conversation, Amplification, Applause, Economic Value,” (2011). [Online]. Available: https://www.kaushik.net/avinash/best-social-media-metrics-conversation-amplification-applause-economic-value/. [Accessed: May 21, 2019].
[27] A. Kaushik, “Best Web Metrics / KPIs for a Small, Medium or Large Sized Business,” (2011). [Online]. Available: https://www.kaushik.net/avinash/best-web-metrics-kpis-small-medium-large-business/. [Accessed: Feb. 5, 2020].
[28] S. Kumar, H. Liu, S. Mehta, and L. V. Subramaniam, “From Tweets to Events: Exploring a Scalable Solution for Twitter Streams,” unpublished manuscript, arXiv preprint, arXiv:1405.1392 (2014).
[29] H. Kwak, C. Lee, H. Park, and S. Moon, “What is Twitter, a social network or a news media?” in Proceedings of the 19th International Conference on World Wide Web, pp. 591-600 (2010).
[30] T. Laor, “Twitter as a clique: journalists’ patterns of Twitter use in Israel”, Online Information Review, Vol. 46 No. 1, pp. 40-58 (2022). https://doi.org/10.1108/OIR-07-2020-0324.
[31] J. Li and C. Cardie, “Timeline Generation: Tracking individuals on Twitter,” in Proceedings of the 23rd International Conference on World Wide Web, pp. 643-652 (2014).
[32] Z. Liu, L. Liu, and H. Li, “Determinants of information retweeting in microblogging”, Internet Research, Vol. 22 No. 4, pp. 443-466 (2012). https://doi.org/10.1108/10662241211250980.
[33] J. F. López, “Coeficiente de determinación (R cuadrado) - Qué es, definición y concepto,” (2017). [Online]. Available: https://economipedia.com/definiciones/r-cuadrado-coeficiente-determinacion.html. [Accessed: Nov. 22, 2020].
[34] J. F. López, “Homocedasticidad - Qué es, definición y concepto,” (2017). [Online]. Available: https://economipedia.com/definiciones/homocedasticidad.html. [Accessed: Dec. 18, 2020].
[35] P. Malhotra and S. K. Malik, “Fake news detection using supervised machine learning techniques”, Journal of Information and Optimization Sciences, Vol. 43 No. 1, pp. 7–15 (2022). https://doi.org/10.1080/02522667.2022.2038933.
[36] M. Muñoz-Expósito, M. Á. Oviedo-García, and M. Castellanos-Verdugo, “How to measure engagement in Twitter: Advancing a metric,” Internet Research, vol. 27, no. 5, pp. 1122-1148 (2017). [Online]. Available: https://doi.org/10.1108/IntR-06-2016-0170.
[37] A. Navarro, F. Utzet, P. Puig, J. Caminal, and M. Martín, “Negative binomial distribution versus Poisson in the analysis of recurrent phenomena,” Gaceta Sanitaria / S.E.S.P.A.S, vol. 15, no. 5, pp. 447-452 (2001). [Online]. Available: https://doi.org/10.1016/S0213-9111(01)71599-3.
[38] J. M. Noguera, “La convergencia entre cibermedios y blogosfera: apuntes para entrar de forma natural en la conversación”, Temas de Comunicación, Vol. 18, pp.135–151 (2009).
[39] B. Omar, H. Al-Samarraie, and B. Wright, “Immediacy as news experience: exploring its multiple dimensions in print and online contexts”, Online Information Review, Vol. 45 No. 2, pp. 461-480 (2021). https://doi.org/10.1108/OIR-12-2019-0388.
[40] C. Orellana-Rodriguez and M. T. Keane, “Attention to news and its dissemination on Twitter: A survey”, Computer Science Review, Vol. 29, pp. 74–94 (2018). https://doi.org/10.1016/j.cosrev.2018.07.001.
[41] D. Peña, Fundamentos de estadística, Alianza editorial, Madrid (2014).
[42] C. Peñafiel Sáiz, “Reinvención del periodismo en el ecosistema digital y narrativas transmedia”, AdComunica, Vol. 12, pp.163–182 (2016).
[43] P. Recuero de los Santos, “Datos de entrenamiento vs datos de test,” (2020). [Online]. Available: https://empresas.blogthinkbig.com/datos-entrenamiento-vs-datos-de-test/. [Accessed: Nov. 22, 2020].
[44] L. Rodríguez Martínez, “5 indicadores clave para medir la interacción en las redes sociales,” (2013). [Online]. Available: https://www.puromarketing.com/42/16086/indicadores-clave-para-medir-interaccionredes-sociales.html. [Accessed: May 21, 2019].
[45] W. Ryan, W. R. Hazlewood, and K. Makice, “Twitterspace: A co-developed display using Twitter to enhance community awareness,” in Proceedings of the Tenth Conference on Participatory Design, pp. 230–233 (2008). [Online]. Available: https://doi.org/10.1145/1795234.1795284.
[46] N. Savage, “Twitter as medium and message”, Communications of the ACM, Vol. 54, No. 3, pp. 18–20 (2011). https://doi.org/10.1145/1897852.1897860
[47] M. Schudson, “The crisis in news: Can you whistle a happy tune?” in The Crisis of Journalism Reconsidered: Democratic Culture, Professional Codes, Digital Future, Cambridge University Press, pp. 98–115 (2016).
[48] C. M. Segijn, E. Maslowska, T. Araujo, and V. Viswanathan, “Engaging with TV events on Twitter: The interrelations between TV consumption, engagement actors, and engagement content”, Internet Research, Vol. 30 No. 2, pp. 381-401 (2019). https://doi.org/10.1108/INTR-08-2018-0389
[49] A. Shiri, “Cybermetrics: A New Horizon in Information Research”, Cybermetrics, Vol. 50, p. 111 (1998).
[50] R. G. D. Steel and J. H. Torrie, Principles and procedures of statistics, McGraw-Hill Book Company, Inc, New York, Toronto, London (1960).
[51] B. Suh, L. Hong, P. Pirolli, and E. H. Chi, “Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network”, 2010 IEEE Second International Conference on Social Computing, pp. 177–184 (2010). https://doi.org/10.1109/SocialCom.2010.33.
[52] J. Teevan, D. Ramage, and M. R. Morris, “#TwitterSearch: A Comparison of Microblog Search and Web Search”, Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, pp. 35–44 (2011).
[53] M. Thelwall and B. Cugelman, “Monitoring Twitter strategies to discover resonating topics: The case of the UNDP,” El Profesional de La Información, vol. 26, no. 4 (2017). [Online]. Available: https://doi.org/10.3145/epi.2017.jul.09.
[54] Twitter Developers, “GET followers/ids,” (2020). [Online]. Available: https://developer.twitter.com/en/docs/accounts-and-users/follow-search-get-users/api-reference/get-followers-ids. [Accessed: Aug. 7, 2020].
[55] Twitter Developers, “GET statuses/user_timeline,” (2020). [Online]. Available: https://developer.twitter.com/en/docs/tweets/timelines/api-reference/get-statuses-user_timeline. [Accessed: Jun. 30, 2020].
[56] Twitter Developers, “Pricing,” (2020). [Online]. Available: https://developer.twitter.com/en/pricing. [Accessed: Jun. 23, 2020].
[57] Twitter Developers, “Rate limiting,” (2020). [Online]. Available: https://developer.twitter.com/en/docs/basics/rate-limiting. [Accessed: Aug. 7, 2020].
[58] Twitter Developers, “Standard search API,” (2020). [Online]. Available: https://developer.twitter.com/en/docs/tweets/search/api-reference/get-search-tweets. [Accessed: Jun. 30, 2020].
[59] Twitter Developers, “Things every developer should know,” (2020). [Online]. Available: https://developer.twitter.com/en/docs/basics/thingsevery-developer-should-know. [Accessed: Aug. 7, 2020].
[60] J. Yang and S. Counts, “Predicting the Speed, Scale, and Range of Information Diffusion in Twitter”, Fourth International AAAI Conference on Weblogs and Social Media, pp. 355-358 (2010). https://doi.org/10.1609/icwsm.v4i1.14039.
[61] A. Zubiaga, D. Spina, R. Martínez, and V. Fresno, “Real-time classification of Twitter trends”, Journal of the Association for Information Science and Technology, Vol. 66 No. 3, pp. 462–473 (2015). https://doi.org/10.1002/asi.23186
[62] D. Zumstein and M. Kaufmann, “A fuzzy Web analytics model for Web mining”, Proceedings of Data Mining 2009, pp. 59–66 (2009).

Views: 209Downloads: 75Citations: 0