Abstract
In order to monitor and detect hot topics in real time, this paper proposes a dynamic detection method for microblog topics based on time series. Firstly, according to the law of event development, a three-level topic evolution model based on time series is proposed, and the microblog text is divided into time slices. Then, a time decay function is introduced, regards it as time feature, use it and content feature together to calculate the text similarity. Finally, the traditional Single-pass algorithm has been improved to optimize its clustering center update strategy. Experiments show that the proposed method has certain improvements in both missed detection rate and false detection rate compared with the Single-Pass algorithm and the IEED algorithm, and can detect the microblog hotspot events in real time dynamically.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
He, M., et al.: Weibo hot topic discovery method based on meaningful cluster clustering. Corr. Technol. 34(S1), 256–262 (2013)
Sayyadi, H., Hurst, M., Maykov, A.: Event detection and tracking in social streams. In: Proceedings of the 3rd International AAAI Conference on Weblogs and Social Media (ICWSM 2009), San Jose, 17–20 May 2009, pp. 311–314 (2009)
Shiren, Y., Ying, Y., Changchun, Y., Mingfeng, Z.: Weibo topic detection method combined with isolated point preprocessing and single-pass clustering. J. Comput. Appl. 33(08), 2294–2297 (2016)
Jiang, Z., et al.: Supervised search result diversification via subtopic attention. IEEE Trans. Knowl. Data Eng. (2018)
Ning, B., et al.: Low-cost message-driven frequency-hopping scheme based on slow frequency-hopping. IET Commun. 12(4), 485–490 (2018)
Run-Nian, M.A., et al.: Evaluation method for node importance in communication network based on mutual information. Acta Electronica Sinica 45(3), 747–752 (2017)
Wang, X., Zuo, M., Song, L.A.: Feature selection method based on information gain and BP neural network. In: Proceedings of 2017 Chinese Intelligent Systems Conference, pp. 23–30 (2018)
Li, H.: Dynamic personalized recommendation algorithm based on ontology similarity and time decay. Libr. Inf. Serv. pp. 95–98 (2017)(s1)
Li, H., Zhu, X.: Microblogging emerging hot event detection based on influence. Comput. Appl. Softw. 33(05), 98–101 + 165 (2016)
Xuejuan, L., Jiabin, Y., Fengping, C.: K-means clustering algorithm for data distribution in cloud computing environment. Miniature Microcomput. Syst. 38(4), 712–715 (2017)
Hong, W., Lina, G., Suqing, W., Liying, W., Yipeng, Z., Yucheng, L.: Improvement of differential privacy protection algorithm based on OPTICS clustering. J. Comput. Appl. 38(01), 73–78 (2018)
Huang, J., Peng, M., Wang, H., Cao, J., Gao, W., Zhang, X.: A probabilistic method for emerging topic tracking in microblog stream. World Wide Web 20(2), 325–350 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, D., Han, Y., Li, X. (2018). Dynamic Detection Method of Micro-blog Topic Based on Time Series. In: Zhou, Q., Miao, Q., Wang, H., Xie, W., Wang, Y., Lu, Z. (eds) Data Science. ICPCSEE 2018. Communications in Computer and Information Science, vol 902. Springer, Singapore. https://doi.org/10.1007/978-981-13-2206-8_17
Download citation
DOI: https://doi.org/10.1007/978-981-13-2206-8_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2205-1
Online ISBN: 978-981-13-2206-8
eBook Packages: Computer ScienceComputer Science (R0)