Skip to main content
SpringerLink
Log in

Topic Detection for Post Bar Based on LDA Model

  • Conference paper
  • First Online:
Data Science (ICPCSEE 2018)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 902))

Abstract

Since most college students use social networks in their daily lives, analysing them would help teachers grasp their students’ thoughts and be consulted for ideological education. This paper aims to extract valuable information and analyse the topic distribution from a large number of posts on the Baidu Post Bar (BPB) using topic detection technologies. We first crawled the post’s data from ten colleges’ post bars and carried out topic detection based on the LDA model. We defined the word weight according to the tf-idf, length, cover and whether it was in the title. We also defined the topic heat ranking model according to the support documents, reply and time coverage. Two label words were automatically selected to represent the topics’ meaning. Then, we analysed the topic distributions. The results of the empirical research showed that college students focused on topics of graduate, work, examinations, learning, campus life and consultation. They paid little attention in politics and society. Finally, we proposed suggestions to the colleges.

Supported by “Innovation and entrepreneurship project of college students in Huazhong University of Science and Technology: The study of Chinese undergraduates’ ideological trend on the social platform”.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://tieba.baidu.com/f/fdir fd = University &i.e. = utf-8&sd = Henan College &i.e. = utf-8.

  2. 2.

    https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/doc2vec-lee.ipynb.

  3. 3.

    http://gaokao.chsi.com.cn/gkxx/zszcgd/dnzszc/201706/20170615/1611254988.html.

  4. 4.

    http://scikit-learn.org/stable/modules/generated/sklearn.cluster.SpectralClustering.html.

  5. 5.

    http://ictclas.nlpir.org.

  6. 6.

    https://radimrehurek.com/gensim/models/ldamodel.html.

References

  1. Zhao, H.W.: Research on the impacts of Baidu Post Bar to high technology students’ value. J. Guilin Univ. Areospace Technol. 21(2), 204–208 (2016)

    Google Scholar 

  2. Yang, X.Y., et al.: Analysis on the status of maintaining stability and network public opinion in Colleges and universities in Dalian – take WeChat, micro-blog, and Baidu on the bar as an example. Intelligence 17, 206 (2017)

    Google Scholar 

  3. Lin, X.F., Xiao, Z.: Hot spot analysis of public opinion based on the BBS forum of college students– Taking Wuhan University LUOJIASHAN water forum as an example. Morden Bus. Trade Ind. 18, 188–189 (2010)

    Google Scholar 

  4. Teng, Y., Chen, L.: An empirical study on the characteristics of network public opinion– text analysis based on BBS forum in Colleges and Universities. Shandong Soc. Sci. 03, 181–186 (2014)

    Google Scholar 

  5. Fang, X.F., Huang, X.X., Wang, R.B.: Hot topic recognition of mobile complaint text based on LDA model. New Technol. Libr. Inf. Serv. 1(2), 19–27 (2017)

    Google Scholar 

  6. Zhang, H.L.: Large text corpus analysis and hot topic discovery based on word co-occurrence network. Comput. Digit. Eng. 10, 1729–1735 (2015)

    Google Scholar 

  7. Chen, X.G.: Research on fast self-clustering method of micro-blog public opinion based on large data technology. J. Intell. 36(5), 113–117 (2017)

    Google Scholar 

  8. He, M.: Feature driven microblog topic detection. J. Chin. Inf. Process. 31(3), 101–108 (2017)

    Google Scholar 

  9. Hao, X.L.: Research on hot topic mining based on economic forum data. Inf. Sci. 34(5), 153–158 (2016)

    Google Scholar 

  10. Wang, X.T., Wang, L.: Analysis of hot word information of online tourism based on text mining – take ctrip as an example. Inf. Stud. Theor. Appl. 40(11), 105–109 (2017)

    Google Scholar 

  11. Yuan, J., Huang, J.J., Tang, X.P.: The analysis of the public opinion of college students in Xinjiang and Countermeasures. Heihe J. 1, 160–162 (2014)

    Google Scholar 

  12. Li, L.: Characteristics of network public opinion in different colleges and universities in the era of media––Take Baidu Post Bar as example. New Compus 9, 30 (2016)

    Google Scholar 

  13. Lan, K.M.: The System of BBS Hot Topic Detection and Monitoring. Beijing Jiaotong University, Beijing (2011)

    Google Scholar 

  14. Wang, X.H.: Hot topic discovery method and system of campus forum based on topic extension. J. Tibet Univ. (Nat. Sci.) 31(02), 110–116 (2016)

    Google Scholar 

  15. Li, Y.F., Chen, L.: Hot topic mining of network forum based on improved BP network. Comput. Syst. Appl. 25(03), 113–118 (2016)

    Google Scholar 

  16. Chen, Y., Cheng, X.Q., Yang, S.: High quality topic discovery for network forums. J. Softw. 22(08), 1785–1804 (2011)

    Article  Google Scholar 

  17. Ibrahim, R., et al.: Tools and approaches for topic detection from Twitter streams: survey. Knowl. Inf. Syst. 6, 1–29 (2017)

    MathSciNet  Google Scholar 

  18. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)

    MATH  Google Scholar 

  19. Blei, D.M., Lafferty, J.D.: Dynamic topic models. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 113–120. ACM (2006)

    Google Scholar 

  20. Weng, J., Lim, E.P., Jiang, J., et al.: TwitterRank: finding topic-sensitive influential Twitterers. In: Proceedings of the 3rd ACM International Conference on Web Search and Data Mining, pp. 261–270. ACM (2010)

    Google Scholar 

  21. Hong, L., Davison, B.D.: Empirical study of topic modeling in Twitter. In: Proceedings of the 1st Workshop on Social Media Analytic, pp. 80–88. ACM (2010)

    Google Scholar 

  22. Zhao, W.X., et al.: Comparing Twitter and traditional media using topic models. In: Clough, P., et al. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338–349. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20161-5_34

    Chapter  Google Scholar 

  23. Ramage, D., Hall, D., Nallapati, R., et al.: Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 248–256 (2009)

    Google Scholar 

  24. Zhang, C.Y., Sun, J.L., Ding, Y.Q.: Topic mining for microblog based on MB-LDA model. J. Comput. Res. Develop. 48(10), 1795–1802 (2011)

    Google Scholar 

  25. Yu, B.G., Zhang, W.C., Wang, F.L.: Topic detection and evolution analysis based on improved OLDA model. J. Intell. 36(2), p. 102 (2017)

    Google Scholar 

  26. Hong, L., Davison, B.D.: Empirical study of topic modeling in Twitter. In: Proceedings of the SIGKDD Workshop on Social Media Analytics, pp. 80–88 (2010)

    Google Scholar 

  27. Rosen-Zvi, M., Griffiths, T., Steyvers, M., et al.: The author-topic model for authors and documents, pp. 487–494 (2012)

    Google Scholar 

  28. Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Advances in Neural Information Processing Systems, pp. 849–856 (2002)

    Google Scholar 

  29. Li, H., Mu, L.L., Zan, H.Y.: Computation of word similarity based on the information content of sememes and pagerank algorithm. Chinese Lexical Semantics. LNCS (LNAI), vol. 10085, pp. 416–425. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49508-8_39

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Public Administration, Huazhong University of Science and Technology, Wuhan, 430074, Hubei, China

    Muzhen Sun

  2. College of Information Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, China

    Haonan Zheng

Authors
  1. Muzhen Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haonan Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muzhen Sun .

Editor information

Editors and Affiliations

  1. Zhengzhou University, Zhengzhou, Henan, China

    Qinglei Zhou

  2. Xidian University, Xi’an, Shaanxi, China

    Qiguang Miao

  3. Harbin Institute of Technology, Harbin, China

    Hongzhi Wang

  4. Harbin University of Science and Technology, Harbin, China

    Wei Xie

  5. Zhengzhou Institute of Technology, Zhengzhou, China

    Yan Wang

  6. National Academy of Guo Ding Institute of Data Science, Beijing, China

    Zeguang Lu

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Sun, M., Zheng, H. (2018). Topic Detection for Post Bar Based on LDA Model. 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_13

Download citation

  • DOI: https://doi.org/10.1007/978-981-13-2206-8_13

  • 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)

Publish with us

Policies and ethics

Search

Navigation