Abstract
First Story Detection (FSD) in twitter stream is to identify the first report that discusses an event that has not been reported in the posted tweets. FSD offers great assistance for New Event Detection (NED). Traditional methods used online clustering framework as mainstream solutions, but suffering low efficiency and unsatisfied performance and did not consider the event related features. We merge event related features and propose event-profile based FSD method based on online cluster framework. It outperforms traditional methods both in efficiency and effect by replacing tweet-by-tweet comparison with profile-by-profile comparison. In this paper, we take four groups of features into account and propose a learning method for the generation of event profile. Experiments show that the profile produced by our method is more relevant with event, also more robust than the ones produced by rule-based methods, eventually, improves the FSD performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allan, J.: Introduction to topic detection and tracking. In: Topic Detection and Tracking. The Information Retrieval Series, vol. 12, pp. 1–16 (2002)
McMinn, A.J., Moshfeghi, Y., Jose, J.M.: Building a large-scale corpus for evaluating event detection on twitter. In: CIKM, pp. 409–418 (2013)
Petrovic, S., Osborne, M., McCreadie, R., et al.: Can Twitter replace Newswire for breaking news? (2013)
Petrovic, S., Osborne, M., Lavrenko, V.: Streaming first story detection with application to twitter. In: NAACL, pp. 181–189 (2010)
Yang, Y., Pierce, T., Carbonell, J.: A study of retrospective and on-line event detection. In: SIGIR, pp. 28–36 (1998)
Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. VLDB 99(6), 518–529 (1999)
Petrovic, S., Osborne, M., Lavrenko, V.: Using paraphrases for improving first story detection in news and Twitter. In: NAACL, pp. 338–346 (2012)
Qiu, Y., Li, S., Li, R.: Nugget-based first story detection in twitter stream. In: SMP, pp. 74–82 (2015)
Sankaranarayanan, J., Samet, H., Teitler, B.E.: Twitterstand: news in tweets. In: SIGSPATIAL 2009, pp. 42–51 (2009)
Becker, H., Naaman, M., Gravano, L.: Beyond trending topics: real-world event identification on twitter (2011)
Allan, J., Lavrenko, V., Jin, H.: First story detection in TDT is hard. In: CIKM, pp. 374–381 (2000)
Allan, J., Papka, R., Lavrenko, V.: On-line new event detection and tracking. In: SIGIR, pp. 37–45 (1998)
Allan, J.: Topic Detection and Tracking: Eventbased Information Organization, pp. 111–122. Kluwer Academic Publishers (2002)
Petrovic, S., Osborne, M., Lavrenko, V.: The edinburgh twitter corpus. In: NAACL, pp. 25–26 (2010)
Phuvipadawat, S., Murata, T.: Breaking news detection and tracking in twitter. In: WI-IAT, pp. 120–123 (2010)
Acknowledgments
We would like to thank the anonymous reviewers for their valuable comments and suggestions. This work is supported by the National Natural Science Foundation of China (grant No. 61572494), the Strategic Priority Research Program of the Chinese Academy of Sciences (grant No. XDA06030200), and the National Key Technology R and D Program (grant No. 2012BAH46B03).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Qiu, Y., Li, R., Wang, L., Wang, B. (2016). Learning Event Profile for Improving First Story Detection in Twitter Stream. In: Cellary, W., Mokbel, M., Wang, J., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2016. WISE 2016. Lecture Notes in Computer Science(), vol 10041. Springer, Cham. https://doi.org/10.1007/978-3-319-48740-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-48740-3_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48739-7
Online ISBN: 978-3-319-48740-3
eBook Packages: Computer ScienceComputer Science (R0)