Caracterização Sócio-Temporal de Conteúdos em Redes Sociais baseada em Processamento em Fluxo
Resumo
A velocidade e a dinâmica de propagação de assuntos veiculados no Twitter caracterizam a plataforma como uma fonte de dados ininterrupta. Este artigo propõe uma abordagem distribuída baseada em métricas de redes complexas para a caracterização socio-temporal de dados textuais provenientes do Twitter. A proposta integra o Apache Kafka na ingestão dos dados e o Apache Spark Streaming no processamento em fluxo dos dados para garantir a captura contínua e o processamento eficiente do conteúdo de diferentes fontes. A proposta identifica, correlaciona e monitora o uso de hashtags em tempo real, através de uma estrutura de grafo dinâmica, gerando uma ontologia sobre o tópico de interesse. Diferente de trabalhos anteriores, que empregam dados históricos, a proposta é aplicada a um caso de uso real com grande repercussão e engajamento dos usuários do Twitter. Avaliando as flutuações de métricas como centralidade, diâmetro e densidade para múltiplas componentes do grafo de hashtags, os resultados revelam tendências de escrita e padrões de relacionamento que reforçam a sensação de câmaras de eco e oportunismo midiático na lógica de utilização de hashtags.
Referências
Alsini, A., Datta, A. e Huynh, D. Q. (2020). On utilizing communities detected from IEEE Transactions on Computational social networks in hashtag recommendation. Social Systems, 7(4):971–982.
Chen, X., Zhou, X., Sellis, T. e Li, X. (2018). Social event detection with retweeting behavior correlation. Expert Systems with Applications, 114:516–523.
Cilibrasi, R. L. e Vitanyi, P. M. (2007). The google similarity distance. IEEE Transactions on knowledge and data engineering, 19(3):370–383.
Colleoni, E., Rozza, A. e Arvidsson, A. (2014). Echo chamber or public sphere? predicting political orientation and measuring political homophily in twitter using big data. Journal of Communication, 64(2):317–332.
Cossard, A., De Francisci Morales, G., Kalimeri, K., Mejova, Y., Paolotti, D. e Starnini, M. (2020). Falling into the echo chamber: The italian vaccination debate on twitter. Em Proceedings of the International AAAI Conference on Web and Social Media, volume 14, p. 130–140.
Cui, A., Zhang, M., Liu, Y., Ma, S. e Zhang, K. (2012). Discover breaking events with popular hashtags in twitter. Em Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM ’12, p. 1794–1798, New York, NY, USA. Association for Computing Machinery.
de Oliveira, N. R., Medeiros, D. S. V. e Mattos, D. M. (2020). A syntactic-relationship approach to construct well-informative knowledge graphs representation. Em 2020 4th Conference on Cloud and Internet of Things (CIoT), p. 75–82.
de Oliveira, N. R., Pisa, P. S., Lopez, M. A., de Medeiros, D. S. V. e Mattos, D. M. F. (2021). Identifying fake news on social networks based on natural language processing: Trends and challenges. Information, 12(1).
Giridhar, P., Wang, S., Abdelzaher, T., Amin, T. A. e Kaplan, L. (2017). Social fusion: Integrating twitter and instagram for event monitoring. Em 2017 IEEE International Conference on Autonomic Computing (ICAC), p. 1–10.
Huang, J., Tang, Y., Hu, Y., Li, J. e Hu, C. (2020). Predicting the active period of popularity evolution: A case study on twitter hashtags. Information Sciences, 512:315–326.
Kowald, D., Pujari, S. C. e Lex, E. (2017). Temporal effects on hashtag reuse in twitter: A cognitive-inspired hashtag recommendation approach. Em Proceedings of the 26th International Conference on World Wide Web, WWW ’17, p. 1401–1410. International World Wide Web Conferences Steering Committee.
Liu, J., He, Z. e Huang, Y. (2018). Hashtag2vec: Learning hashtag representation with relational hierarchical embedding model. Em Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, p. 3456–3462. International Joint Conferences on Artificial Intelligence Organization.
Liu, X. e Buyya, R. (2020). Resource management and scheduling in distributed stream processing systems: A taxonomy, review, and future directions. ACM Comput. Surv., 53(3).
Lopez, M. A., Lobato, A. G. P. e Duarte, O. C. M. B. (2016a). Monitoramento de tráfego e detecção de ameaças por sistemas distribudos de processamento de fluxos: uma análise de desempenho. Em Anais do XXI Workshop de Gerência e Operação de Redes e Serviços. SBC.
Lopez, M. A., Lobato, A. G. P. e Duarte, O. C. M. B. (2016b). A performance comparison of open-source stream processing platforms. Em 2016 IEEE Global Communications Conference (GLOBECOM), p. 1–6.
Nasiri, H., Nasehi, S. e Goudarzi, M. (2019). Evaluation of distributed stream processing frameworks for iot applications in smart cities. Journal of Big Data, 6(1):52.
Rao, T. R., Mitra, P., Bhatt, R. e Goswami, A. (2019). The big data system, components, tools, and technologies: a survey. Knowledge and Information Systems, 60(3):1165– 1245.
Stilo, G. e Velardi, P. (2017). Hashtag sense clustering based on temporal similarity. Comput. Linguist., 43(1):181–200.
Sun, A. Y., Zhong, Z., Jeong, H. e Yang, Q. (2019). Building complex event processing capability for intelligent environmental monitoring. Environmental Modelling & Software, 116:1–6.
Vicario, M. D., Vivaldo, G., Bessi, A., Zollo, F., Scala, A., Caldarelli, G. e Quattrociocchi, W. (2016). Echo chambers: Emotional contagion and group polarization on facebook. Scientific Reports, 6.
Wang, Y., Liu, J., Huang, Y. e Feng, X. (2016). Using hashtag graph-based topic model IEEE to connect semantically-related words without co-occurrence in microblogs. Transactions on Knowledge and Data Engineering, 28(7):1919–1933.
Yadranjiaghdam, B., Yasrobi, S. e Tabrizi, N. (2017). Developing a real-time data analytics framework for twitter streaming data. Em 2017 IEEE International Congress on Big Data (BigData Congress), p. 329–336.
Yang, C., Wang, X. e Jiang, B. (2020). Sentiment enhanced multi-modal hashtag recommendation for micro-videos. IEEE Access, 8:78252–78264.
Zhang, Y. (2019). Language in our time: An empirical analysis of hashtags. Em The World Wide Web Conference, WWW ’19, p. 2378–2389, New York, NY, USA. Association for Computing Machinery.
Chen, X., Zhou, X., Sellis, T. e Li, X. (2018). Social event detection with retweeting behavior correlation. Expert Systems with Applications, 114:516–523.
Cilibrasi, R. L. e Vitanyi, P. M. (2007). The google similarity distance. IEEE Transactions on knowledge and data engineering, 19(3):370–383.
Colleoni, E., Rozza, A. e Arvidsson, A. (2014). Echo chamber or public sphere? predicting political orientation and measuring political homophily in twitter using big data. Journal of Communication, 64(2):317–332.
Cossard, A., De Francisci Morales, G., Kalimeri, K., Mejova, Y., Paolotti, D. e Starnini, M. (2020). Falling into the echo chamber: The italian vaccination debate on twitter. Em Proceedings of the International AAAI Conference on Web and Social Media, volume 14, p. 130–140.
Cui, A., Zhang, M., Liu, Y., Ma, S. e Zhang, K. (2012). Discover breaking events with popular hashtags in twitter. Em Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM ’12, p. 1794–1798, New York, NY, USA. Association for Computing Machinery.
de Oliveira, N. R., Medeiros, D. S. V. e Mattos, D. M. (2020). A syntactic-relationship approach to construct well-informative knowledge graphs representation. Em 2020 4th Conference on Cloud and Internet of Things (CIoT), p. 75–82.
de Oliveira, N. R., Pisa, P. S., Lopez, M. A., de Medeiros, D. S. V. e Mattos, D. M. F. (2021). Identifying fake news on social networks based on natural language processing: Trends and challenges. Information, 12(1).
Giridhar, P., Wang, S., Abdelzaher, T., Amin, T. A. e Kaplan, L. (2017). Social fusion: Integrating twitter and instagram for event monitoring. Em 2017 IEEE International Conference on Autonomic Computing (ICAC), p. 1–10.
Huang, J., Tang, Y., Hu, Y., Li, J. e Hu, C. (2020). Predicting the active period of popularity evolution: A case study on twitter hashtags. Information Sciences, 512:315–326.
Kowald, D., Pujari, S. C. e Lex, E. (2017). Temporal effects on hashtag reuse in twitter: A cognitive-inspired hashtag recommendation approach. Em Proceedings of the 26th International Conference on World Wide Web, WWW ’17, p. 1401–1410. International World Wide Web Conferences Steering Committee.
Liu, J., He, Z. e Huang, Y. (2018). Hashtag2vec: Learning hashtag representation with relational hierarchical embedding model. Em Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, p. 3456–3462. International Joint Conferences on Artificial Intelligence Organization.
Liu, X. e Buyya, R. (2020). Resource management and scheduling in distributed stream processing systems: A taxonomy, review, and future directions. ACM Comput. Surv., 53(3).
Lopez, M. A., Lobato, A. G. P. e Duarte, O. C. M. B. (2016a). Monitoramento de tráfego e detecção de ameaças por sistemas distribudos de processamento de fluxos: uma análise de desempenho. Em Anais do XXI Workshop de Gerência e Operação de Redes e Serviços. SBC.
Lopez, M. A., Lobato, A. G. P. e Duarte, O. C. M. B. (2016b). A performance comparison of open-source stream processing platforms. Em 2016 IEEE Global Communications Conference (GLOBECOM), p. 1–6.
Nasiri, H., Nasehi, S. e Goudarzi, M. (2019). Evaluation of distributed stream processing frameworks for iot applications in smart cities. Journal of Big Data, 6(1):52.
Rao, T. R., Mitra, P., Bhatt, R. e Goswami, A. (2019). The big data system, components, tools, and technologies: a survey. Knowledge and Information Systems, 60(3):1165– 1245.
Stilo, G. e Velardi, P. (2017). Hashtag sense clustering based on temporal similarity. Comput. Linguist., 43(1):181–200.
Sun, A. Y., Zhong, Z., Jeong, H. e Yang, Q. (2019). Building complex event processing capability for intelligent environmental monitoring. Environmental Modelling & Software, 116:1–6.
Vicario, M. D., Vivaldo, G., Bessi, A., Zollo, F., Scala, A., Caldarelli, G. e Quattrociocchi, W. (2016). Echo chambers: Emotional contagion and group polarization on facebook. Scientific Reports, 6.
Wang, Y., Liu, J., Huang, Y. e Feng, X. (2016). Using hashtag graph-based topic model IEEE to connect semantically-related words without co-occurrence in microblogs. Transactions on Knowledge and Data Engineering, 28(7):1919–1933.
Yadranjiaghdam, B., Yasrobi, S. e Tabrizi, N. (2017). Developing a real-time data analytics framework for twitter streaming data. Em 2017 IEEE International Congress on Big Data (BigData Congress), p. 329–336.
Yang, C., Wang, X. e Jiang, B. (2020). Sentiment enhanced multi-modal hashtag recommendation for micro-videos. IEEE Access, 8:78252–78264.
Zhang, Y. (2019). Language in our time: An empirical analysis of hashtags. Em The World Wide Web Conference, WWW ’19, p. 2378–2389, New York, NY, USA. Association for Computing Machinery.
Publicado
16/08/2021
Como Citar
OLIVEIRA, Nicollas R. de; MEDEIROS, Dianne S. V.; MATTOS, Diogo M. F..
Caracterização Sócio-Temporal de Conteúdos em Redes Sociais baseada em Processamento em Fluxo. In: WORKSHOP DE GERÊNCIA E OPERAÇÃO DE REDES E SERVIÇOS (WGRS), 26. , 2021, Uberlândia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 54-67.
ISSN 2595-2722.
DOI: https://doi.org/10.5753/wgrs.2021.17185.
