Análisis supervisado de sentimientos políticos en españolclasificación en tiempo real de tweets basada en aprendizaje automático

  1. Carlos Arcila Calderón 1
  2. Félix Ortega Mohedano 1
  3. Javier Jiménez Amores 1
  4. Sofía Trullenque 1
  1. 1 Universidad de Salamanca
    info

    Universidad de Salamanca

    Salamanca, España

    ROR https://ror.org/02f40zc51

Revista:
El profesional de la información

ISSN: 1386-6710,  1699-2407

Año de publicación: 2017

Título del ejemplar: Comunicación política II

Volumen: 26

Número: 5

Páginas: 973-982

Tipo: Artículo

DOI: 10.3145/EPI.2017.SEP.18 DIALNET GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: El profesional de la información

Resumen

Se describe y evalúa la aplicación de la técnica análisis supervisado de sentimientos en comunicación política a través de un clasificador en tiempo real de opiniones políticas en tweets en español utilizando técnicas de aprendizaje automático (machine learning), tanto en un ordenador local como usando computación distribuida comercial para problemas de datos masivos (big data). Describimos las técnicas y métodos emergentes asociados y analizamos las oportunidades que para la comunicación política representan estas innovaciones.

€ Ver financiación

Información de financiación

Los autores agradecen a la Fundación General de la Universidad de Salamanca y al Plan TCUE [2015-2017 Fase 2] la financiación obtenida para el desarrollo de la prueba de concepto: Clasificador en tiempo real de opiniones políticas en español con técnicas de aprendizaje automático (Auto-cop).

Financiadores

Referencias bibliográficas

  • Arcila-Calderón, Carlos; Barbosa-Caro, Eduar; Cabezuelo-Lorenzo, Francisco (2016). “Técnicas big data: análisis de textos a gran escala para la investigación científica y periodística”. El profesional de la información, v. 25, n. 4, pp. 623-631. https://doi.org/10.3145/epi.2016.jul.12
  • Bakliwal, Akshat; Arora, Piyush; Madhappan, Senthil; Kapre, Nikhil; Singh, Mukesh; Varma, Vasudeva (2012). “Mining sentiments from tweets”. En: Proceedings of the WASSA 2012, pp. 11-18. http://www.aclweb.org/anthology/W12-3704
  • Bakliwal, Akshat; Foster, Jennifer; Van-der-Puil, Jennifer; O’Brien, Ron; Tounsi, Lamia; Hughes, Mark (2013). “Sentiment analysis of political tweets: Towards an accurate classifier”. En: Proceedings of the Workshop on language in social media Lasm2013, Association for Computational Linguistics, pp. 49-58. http://www.aclweb.org/anthology/W13-1106
  • Bermingham, Adam; Smeaton, Alan (2010). “Classifying sentiment in microblogs: is brevity an advantage?”. En: Proceedings of the 19th ACM Intl conf on information and knowledge management, pp. 1833-1836. https://core.ac.uk/download/pdf/11309792.pdf
  • Bermingham, Adam; Smeaton, Alan (2011). “On using Twitter to monitor political sentiment and predict election results”. En: Proceedings of the Workshop on sentiment analysis where AI meets psychology (Saaip), Ijcnllp 2011, pp. 2-10. https://www.aclweb.org/anthology/W/W11/W11-3702.pdf
  • Bollen, Johan; Mao, Huina; Pepe, Alberto (2011). “Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena”. En: Proceedings of the Fifth Intl AAAI conf on weblogs and social media. AAAI-Icwsm 2011. Association for the Advancement of Artificial Intelligence, pp. 450-453. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/ paper/viewFile/2826/3237
  • Bučar, Jože; Povh, Janez; ŽnidarÅ¡ič, Martin (2016). “Sentiment classification of the Slovenian news texts”. En: Proceedings of the 9th Intl conf on computer recognition systems (Cores 2015), pp. 777-787. https://doi.org/10.1007/978-3-319-26227-7_73
  • Cambria, Erik; Schuller, Björn; Liu, Bing; Wang, Haixun; Havasi, Catherine (2013). “Knowledge-based approaches to concept-level sentiment analysis”. IEEE intelligent systems, v. 28, n. 2, pp. 12-14. https://www.computer.org/csdl/mags/ex/2013/02/ mex2013020012.pdf
  • Choy, Murphy; Cheong, Michelle; Laik, Ma-Nang; Shung, Koo-Ping (2011). “A sentiment analysis of Singapore presidential election 2011 using Twitter data with census correction”. Report: arXiv:1108.5520. https://arxiv.org/ftp/arxiv/papers/1108/1108.5520.pdf
  • Cobb, Wendi-N-Whitman (2015). “Trending now: Using big data to examine public opinion of space policy”. Space policy, v. 32, pp. 11-16. https://doi.org/10.1016/j.spacepol.2015.02.008
  • Feldman, Ronen (2013). “Techniques and applications for sentiment analysis”. Communications of the ACM, v. 56, n. 4, pp. 82-89. https://goo.gl/xW9veE https://doi.org/10.1145/2436256.2436274
  • García-Cumbreras, Miguel-Ángel; Villena-Román, Julio; Martínez-Cámara, Eugenio; García-Morera, Janine (2016). “The evolution of the Spanish opinion mining systems”. Procesamiento de lenguaje natural, v. 56, pp. 33-40. http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/ article/view/5284/3078
  • Hurtado, Lluís F.; Pla, Ferran; Buscaldi, Davide (2015). “ELiRF-UPV en TASS 2015: Análisis de sentimientos en Twitter”. En: Proceedings of TASS 2015: Workshop on sentiment analysis at Sepln, pp. 75-79. http://ceur-ws.org/Vol-1397/elirf_upv.pdf
  • Kranjc, Janez; Smailović, Jasmina; Podpečan, Vid; Grčar, Miha; ŽnidarÅ¡ič, Martin; Lavrač, Nada (2015). “Active learning for sentiment analysis on data streams: Methodology and workflow implementation in the ClowdFlows platform”. Information processing & management, v. 51, n. 2, pp. 187-203. https://goo.gl/cnJYJ1 https://doi.org/10.1016/j.ipm.2014.04.001
  • Lampitt, Andrew (2013). “The real story of how big data analytics helped Obama win”. Infoworld, 14 February. http://www.infoworld.com/article/2613587/big-data/thereal-story-of-how-big-data-analytics-helped-obama-win.html
  • Leetaru, Kalev-Hannes (2012). Data mining methods for the content analyst: An introduction to the computational analysis of content. New York: Routledge. ISBN: 978 0 415895149
  • Madlberger, Lisa; Almansour, Amai (2014). “Predictions based on Twitter —A critical view on the research process”. En: Data and software engineering (Icodse), 2014 Intl conf. IEEE, pp. 1-6. https://doi.org/10.1109/ICODSE.2014.7062667
  • Mariño-Angoso, Miguel (2015). “Oracle big data and webdata. What we are doing and future tendencies. Big data environment and Oracle solutions”. En: Conference proceedings, Media metrics and webdata task force, Cost action conference Webdatanet, University of Salamanca, pp. 23-30. http://www.webdatanet.eu/data/167
  • O’Connor, Brendan; Balasubramanyan, Rammnath; Routledge, Bryan-R.; Smith, Noah A. (2010). “From tweets to polls: Linking text sentiment to public opinion time series”. En: Proceedings of the 4th Intl AAAI conf on weblogs and social media, Icwsm 2011, pp.122-129. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/ paper/viewFile/1536/1842
  • Pang, Bo; Lee, Lillian; Vaithyanathan, Shivakumar (2002). “Thumbs up?: sentiment classification using machine learning techniques”. En: Procs of the ACL-02 Conf on empirical methods in natural language processing, v. 10, Association for Computational Linguistics, pp. 79-86. http://www.cs.cornell.edu/home/llee/papers/sentiment.pdf
  • Preethi, Peter G.; Uma, Vilma; Kumar, Ajit (2015). “Temporal sentiment analysis and causal rules extraction from tweets for event prediction”. Procedia computer science, v. 48, pp. 84-89. https://goo.gl/v1Pn3T https://doi.org/10.1016/j.procs.2015.04.154
  • Sluban, Borut; Smailović, Jasmina; Battiston, Stefano; Mozetič, Igor (2015). “Sentiment leaning of influential communities in social networks”. Computational social networks, v. 2, n. 1, pp. 1-21. https://doi.org/10.1186/s40649-015-0016-5
  • Smailović, Jasmina; Grčar, Miha; Lavrač, Nada; ŽnidarÅ¡ič, Martin (2013). “Predictive sentiment analysis of tweets: A stock market application”. Human-computer interaction and knowledge discovery in complex, unstructured, big data. Lecture notes in computer science, v. 7947, pp. 77-88. http://first. i js.si/FirstShowcase/Content/pub/HCIKDD-2013.pdf https://doi.org/10.1007/978-3-642-39146-0_8
  • Smailović, Jasmina; Kranjc, Janez; Grčar, Miha; ŽnidarÅ¡ič, Martin; Mozetič, Igor (2015). “Monitoring the Twitter sentiment during the Bulgarian elections”. En: IEEE Int conf on data science and advanced analytics (DSAA). https://goo.gl/s5WtYA https://doi.org/10.1109/DSAA.2015.7344886
  • Sorrells, Amy (2012). “How big data and social won the election”. Oracle social spotlight, 9 November. https://blogs.oracle.com/socialspotlight/how-big-dataand-social-won-the-election
  • Spark Kafka Integration (2016). Spark Streaming + Kafka Integration Guide. http://spark.apache.org/docs/latest/streaming-kafkaintegration.html
  • Tumasjan, Andranik; Sprenger, Timm O.; Sandner, Phillipp G.; Welpe, Isabell M. (2010). “Predicting elections with Twitter: What 140 characters reveal about political sentiment”. En: Pros of the 4th Intl AAAI conf on weblogs and social media (Icwsm), v. 10, n. 1, pp. 178-185. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/ paper/view/1441
  • Turck, Matt; Hao, Jim (2016). Big data landscape 2016 (Version 3.0). http://mattturck.com/big-data-landscape-2016-v18-final
  • Turney, Peter D. (2002). “Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews”. En: Procs of the 40th Annual meeting on Association for Computational Linguistics, pp. 417-424. http://www.aclweb.org/anthology/P02-1053.pdf
  • Van-Zoonen, Ward; Van-der-Meer, Toni (2016). “Social media research: The application of supervised machine learning in organizational communication research”. Computers in human behavior, v. 63, pp. 132-141. https://doi.org/10.1016/j.chb.2016.05.028
  • Vinodhini, Gina; Chandrasekaran, R. M. (2012). “Sentiment analysis and opinion mining: A survey”. International journal of advanced research in computer science and software engineering, v. 2, n. 6, pp. 282-292. https://goo.gl/c1hWpy
  • Wang, Hao; Can, Dogan; Kazemzadeh, Abe; Bar, François; Narayanan, Shrikanth (2012). “A system for real-time Twitter sentiment analysis of 2012 us presidential election cycle”. En: Procs of the ACL 2012 System demonstrations. Association for Computational Linguistics, pp. 115-120. http://www.aclweb.org/anthology/P12-3020
Fuente de los datos: Dialnet