Abstract
The university online community mainly records what happens in target areas and groups of people. It has the characteristics of timeliness, regional strong and clear target groups. Compared with Weibo and post-bar, university community’s text topic recognition needs to solve the problems of large text noise, fast text update and short single text content. To this end, this paper proposes a method of building university topic model based on LDA topic model. Through the steps of original text’s noise reduction, LDA (Latent Dirichlet Allocation (LDA), is a topic model commonly used in the field of machine learning and is often used for text categorization.) model recognition and weighted calculation of recognition results, etc., the event themes that characterize the common characteristics for university online community are obtained. Experiments based on real university online community’s data show that the topic model of university popular events established by the topic recognition model of this paper can reflect some popular events in colleges and universities, so as to provide reasonable support for university management.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, M., Wang, Y., Gao, S., Wang, H., Zhang, X.: Evolution of topic using LDA model: Evidence From Information Science Journals. J. Beijing Univ. Technol. 07, 1047–1053 (2018)
Peng, Y., Wan, H., Zhong, L.: Fine-grained sentiment analysis algorithm of product reviews based on semantic weakly-supervised LDA. J. Mini-micro Syst. 05, 978–985 (2018)
Yi, H., Wu, H., Ma, Y., Ji, F.: Technical topic analysis in patents based on LDA and strategic diagram by taking graphene technology as an example. J. Intell. 05, 97–102 (2018)
Tan, C., Wang, C., Zhang, Y.: A hot topic identification based on LDA for Chinese microblog. J. Suzhou Univ. 04, 71–77 (2014)
Zheng, Z., Jin, B., Cui, Y.: Study on recognition of spatial-temporal events based on microblogs. J. Comput. Sci. 10, 214–219 (2016)
Xu, B., Zhao, C., Zhang, Y.: Topic community mining in blogosphere based on LDA. J. Comput. Digit. Eng. 11, 40–43 (2012)
Shi, D., Zhang, H.: LDA model-based BBS topic evolution. J. Industr. Control Comput. 05, 82–84 (2012)
He, M., Wang, H., Zhou, L., Wang, P., Ju, A.: Symmetric learning data augmentation model for underwater target noise data expansion. CMC: Comput. Mater. Continua 57(3), 521–532 (2018)
Wang, S., et al.: Natural language semantic construction based on cloud database. CMC: Comput. Mater. Continua 57(3), 603–619 (2018)
A simple web crawler for crawler learning. https://www.cnblogs.com/chenkun/p/5653459.html
Acknowledgements
This work is supported by the National Key Research and Development Plan(Grant No. 2017YFC0820603), BUPT’s Informatization Innovative Application Project, “ privacy protection and data release on Campus big data” and the Open Project Fund of Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, X., Wu, H., Xie, X., Xu, J., Zhang, T. (2019). Short Text Topic Recognition and Optimization Method for University Online Community. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11635. Springer, Cham. https://doi.org/10.1007/978-3-030-24268-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-24268-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24267-1
Online ISBN: 978-3-030-24268-8
eBook Packages: Computer ScienceComputer Science (R0)