Abstract
Social topic detection and analysis has always been one of the hot topics in data mining. In recent years, with the rapid development of Internet technology, the coverage and information volume of social networking data has increased dramatically. The detection of social topics arouses great discussions and inspires extensive researches. The most common method of topic detection is to cluster texts based on textual features or combining textual features and background information. Each cluster obtained represents a topic. This paper proposes a link prediction-based hybrid detection model (LP-HD) which combines text feature extraction and topology network. For topic detection, the model first constructs a topology graph of all features based on corpus. Then it extracts the feature information of each original text to obtain the feature sequence of the text. The information in these feature sequences is added to the topology graph. Every time after a fixed period of time, LP-HD will take a snapshot of the current topology graph and predict the fluctuation range of each edge in the next time window. Combining the current snapshot and the previous snapshot, the actual fluctuation of each edge can be obtained. In combination with the previous forecast, those active edges can be captured. In the end, these active edges define a new hot topic. At the same time, the topics that are being quickly forgotten can be captured through those once active and now inactive edges. In addition, we also analyze the good adaptability of the LP-HD model. Finally, the experiment proves that LP-HD has good performance on both long text and short text in topic detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Endo, Y., Toda, H., Koike, Y.: What’s hot in the theme - query dependent emerging topic extraction from social streams. In: International Conference on World Wide Web (WWW), Florence, Italy, pp. 31–32 (2015)
Khare, P., Torres-Tramón, P., Heravi, B.R.: What just happened? A framework for social event detection and contextualisation. In: Hawaii International Conference on System Sciences (HICSS), Hawaii, USA, pp. 1565–1574 (2015)
Wold, H.M., Vikre, L., Gulla, J.A., Özgöbek, Ö., Su, X.: Twitter topic modeling for breaking news detection. In: International Conference on Web Information Systems and Technologies (WEBIST), Rome, Italy, pp. 211–218 (2016)
Hashimoto, T., Kuboyama, T., Okamoto, H., Shin, K.: Topic extraction on twitter considering author’s role based on bipartite networks. In: International Conference on Discovery Science (DS), vol. 20, pp. 467–476 (2016)
Rafea, A., Mostafa, N.A.: Topic extraction in social media. In: International Conference on Collaboration Technologies and Systems (CTS), pp. 239–247 (2017)
Bao, B.-K., Min, W., Lu, K., Xu, C.: Social event detection with robust high-order co-clustering. In: The ACM International Conference on Multimedia Retrieval (ICMR), London, Banda Aceh, Indonesia, pp. 135–142 (2013)
Wang, Y., Sundaram, H., Xie, L.: Social event detection with interaction graph modeling. In: ACM Multimedia, pp. 865–868 (2012)
Yang, Z., Li, Q., Lu, Z., Ma, Y., Gong, Z., Pan, H.: Semi-supervised multimodal clustering algorithm integrating label signals for social event detection. In: IEEE International Conference on Multimedia Big Data (BigMM), Beijing, China, pp. 32–39 (2015)
Zhang, X., Zheng, N., Xu, J., Xu, M.: Topic detection in group chat based on implicit reply. In: Pacific Rim International Conference on Artificial Intelligence (PRICAI), Phuket, Thailand, pp. 62–75 (2016)
Chakraborty, B., Hashimoto, T.: Topic extraction from messages in social computing services-determining the number of topic clusters. In: IEEE Fourth International Conference on Semantic Computing (ICSC), Pittsburgh, PA, USA, pp. 94–98 (2010)
Wang, Y., Xie, L., Sundaram, H.: Social event detection with clustering and filtering. In: Working Notes Mediaeval Workshop (MediaEval) (2011)
Samangooei, S., Hare, J., Dupplaw, D., Niranjan, M., Gibbins, N., Lewis, P.: Social event detection via sparse multi-modal feature selection and incremental density based clustering. In: Working Notes Mediaeval Workshop (MediaEval) (2013)
Traag, V.A., Browet, A., Calabrese, F., Morlot, F.: Social event detection in massive mobile phone data using probabilistic location inference. In: IEEE International Conference on Privacy, Security, Risk, and Trust, and IEEE International Conference on Social Computing (SocialCom/PASSAT), Boston, MA, USA, pp. 625–628 (2011)
Chen, Q., Guo, X., Bai, H.: Semantic-based topic detection using Markov decision processes. Neurocomputing 242, 40–50 (2017)
Xie, K., Xia, C., Grinberg, N., Schwartz, R., Naaman, M.: Robust detection of hyper-local events from geotagged social media data. In: International Workshop on Multimedia Data Mining (MDMKDD), Chicago, IL, USA, pp. 1–9 (2013)
Osborne, M., Moran, S., McCreadie, R., von Lünen, A., Sykora, M.D., Cano, E., Ireson, N., Macdonald, C., Ounis, I., He, Y., Jackson, T., Ciravegna, F., O’Brien, A.: Real-time detection, tracking, and monitoring of automatically discovered events in social media. In: Association for Computational Linguistics (ACL), Baltimore, MD, USA, pp. 37–42 (2014)
Comito, C., Pizzuti, C., Procopio, N.: Online clustering for topic detection in social data streams. In: IEEE International Conference on Tools with Artificial Intelligence (ICTAI), San Jose, CA, USA, pp. 362–369 (2016)
Liu, Y., Zhou, B., Chen, F., Cheung, D.W.: Graph topic scan statistic for spatial event detection. In: ACM International Conference on Information and Knowledge Management (CIKM), pp. 489-498, Indianapolis, IN, USA (2016)
Hu, W., Wang, H., Qiu, Z., Nie, C., Yan, L., Du, B.: An event detection method for social networks based on hybrid link prediction and quantum swarm intelligent. World Wide Web (WWW) 20, 775–795 (2017)
Hu, J., Li, S., Yao, Y., Yu, L., Yang, G., Hu, J.: Patent keyword extraction algorithm based on distributed representation for patent classification. Entropy 20, 104 (2018)
Biswas, S.K., Bordoloi, M., Shreya, J.: A graph based keyword extraction model using collective node weight. Expert. Syst. Appl. 97, 51–59 (2018)
Zimniewicz, M., Kurowski, K., Weglarz, J.: Scheduling aspects in keyword extraction problem. In: International Transactions in Operational Research (ITOR), vol. 25, pp. 507–522 (2018)
Sørensen, T.: A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on Danish commons. Biol. Skr., 1–34 (1948)
Acknowledgements
This work was supported by the National Key R&D Program of China [2018YFB1004703]; the National Natural Science Foundation of China [61872238, 61672353]; the Shanghai Science and Technology Fund [17510740200]; the Huawei Innovation Research Program [HO2018085286]; and the State Key Laboratory of Air Traffic Management System and Technology [SKLATM20180X].
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
Liu, Q., Gao, X., Chen, G. (2019). LP-HD: An Efficient Hybrid Model for Topic Detection in Social Network. In: Lee, S., Ismail, R., Choo, H. (eds) Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication (IMCOM) 2019. IMCOM 2019. Advances in Intelligent Systems and Computing, vol 935. Springer, Cham. https://doi.org/10.1007/978-3-030-19063-7_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-19063-7_67
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19062-0
Online ISBN: 978-3-030-19063-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)