Abstract
Event summarization based on crowdsourced microblog data is a promising research area, and several researchers have recently focused on this field. However, these previous works fail to characterize the fine-grained evolution of an event and the rich correlations among posts. The semantic associations among the multi-modal data in posts are also not investigated as a means to enhance the summarization performance. To address these issues, this study presents CrowdStory, which aims to characterize an event as a fine-grained, evolutionary, and correlation-rich storyline. A crowd-powered event model and a generic event storyline generation framework are first proposed, based on which a multi-clue--based approach to fine-grained event summarization is presented. The implicit human intelligence (HI) extracted from visual contents and community interactions is then used to identify inter-clue associations. Finally, a cross-media mining approach to selective visual story presentation is proposed. The experiment results indicate that, compared with the state-of-the-art methods, CrowdStory enables fine-grained event summarization (e.g., dynamic evolution) and correctly identifies up to 60% strong correlations (e.g., causality) of clues. The cross-media approach shows diversity and relevancy in visual data selection.
- J. Bian, Y. Yang, H. Zhang, and T. Chua, “Multimedia Summarization for Social Events in Microblog Stream,” IEEE Transactions on multimedia, vol. 17, no. 2, pp. 216--228, 2015.Google ScholarDigital Library
- D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent dirichlet allocation,” Journal of machine Learning research, vol. 3, no.1, pp. 993-1022, 2003. Google Scholar
- F. Buckley and M. Lewinter, “A friendly introduction to graph theory,” Prentice Hall, 2003.Google Scholar
- D. Chakrabarti and K. Punera, “Event Summarization using Tweets,” in Proc. of ICWSM’11, AAAI, 2011, pp. 66--73.Google Scholar
- Y. Chen, et al., “Event detection using customer care calls,” in Proc. of INFOCOM’13, 2013, pp. 1690-1698.Google ScholarCross Ref
- D. Corney, C. Martin, and A. Göker, “Two sides to every story: Subjective event summarization of sports events using Twitter,” in Proc. of the SoMuS ICMR 2014 Workshop, ACM, 2014.Google Scholar
- A. Cui, M. Zhang, Y. Liu, et al., “Discover breaking events with popular hashtags in twitter,” in Proc. of CIKM’12, ACM, 2012, pp. 1794-1798. Google ScholarDigital Library
- N. Dehghani, M. Asadpour, “Graph-based Method for Summarized Storyline Generation in Twitter,” arXiv preprint arXiv:1504.07361, 2015.Google Scholar
- J.L. Fleiss, B. Levin, C.P. Myunghee, “The measurement of interrater agreement. Statistical methods for rates and proportions,” no. 2, pp. 212-236, 1981.Google Scholar
- B. Guo, H. Chen, Z. Yu, X. Xie, S. Huangfu, D. Zhang, “FlierMeet: A Mobile Crowdsensing System for Cross-Space Public Information Reposting, Tagging, and Sharing,” IEEE Transactions on Mobile Computing, vol. 14, no. 10, 2015, pp. 2020-2033. Google ScholarDigital Library
- M. Halkidi, Y. Batistakis, and M. Vazirgiannis, “On clustering validation techniques,” Journal of intelligent information systems, vol. 17, no. 2-3, pp. 107-145, 2001. Google ScholarDigital Library
- T. Hua, X. Zhang, W. Wang, et al., “Automatical Storyline Generation with Help from Twitter,” in Proc. of CIKM’16, ACM, 2016, pp. 2383-2388. Google ScholarDigital Library
- L. Huang and L. Huang, “Optimized Event Storyline Generation based on Mixture-Event-Aspect Model,” in Proc. of EMNLP’13, ACL, 2013, pp. 726--735.Google Scholar
- L. Hubert and P. Arabie, “Comparing partitions,” Journal of classification, vol. 2, no. 1, pp. 193-218, 1985.Google ScholarCross Ref
- J. Kim, A. Monroy-Hernandez, “Storia: Summarizing social media content based on narrative theory using crowdsourcing,” in Proc. of CSCW’16. ACM, 2016, pp. 1018-1027. Google ScholarDigital Library
- J. Kleinberg, D. Easley, Networks, Crowds, and Markets, Cambridge University Press, 2010.Google Scholar
- P. Lee, et al., “CAST: A Context-Aware Story-Teller for Streaming Social Content,” in Proc. of CIKM’14, ACM, 2014, pp. 789-798. Google ScholarDigital Library
- C. Lin, et al., “Generating event storylines from microblogs,” in Proc. of CIKM’15, ACM, 2012, pp. 175-184. Google ScholarDigital Library
- C. Y. Lin, “Rouge: A package for automatic evaluation of summaries,” in Proc. of ACL’04 workshop, 2004, pp. 1-8.Google Scholar
- H. Lin and J. Bilmes, “Multi-document summarization via budgeted maximization of submodular functions,” in Proc. of ACL’10, 2010, pp. 912-920. Google ScholarDigital Library
- D. G. Lowe, “Object recognition from local scale-invariant features,” in Proc. of ICCV’99, 1999, pp. 1150-1157. Google ScholarDigital Library
- M. Mathioudakis, N. Koudas, “TwitterMonitor: trend detection over the Twitter stream,” in Proc. Of SIGMOD’10, ACM, 2010, pp. 1155-1158. Google ScholarDigital Library
- A. J. McMinn, Y. Moshfeghi, and J. M. Jose, “Building a large-scale corpus for evaluating event detection on twitter,” in Proc. of CIKM’13, ACM, 2013, pp. 409-418 Google ScholarDigital Library
- P. Meladianos, et al., “Degeneracy-based real-time sub-event detection in twitter stream,” in Proc. of ICWSM’15, 2015, pp. 248-257.Google Scholar
- J. Nichols, J. Mahmud, and C. Drews, “Summarizing sporting events using twitter,” in Proc. of IUI’12, ACM, 2012, pp. 189-198. Google ScholarDigital Library
- J. Pearl, “Causality,” Cambridge university press, 2009.Google Scholar
- K. Rudra, et al., “Extracting Situational Information from Microblogs during Disaster Events: a Classification-Summarization Approach,” in Proc. of CIKM’15, ACM, 2015, pp. 583-592. Google ScholarDigital Library
- T. Sakaki, M. Okazaki, and Y. Matsuo, “Earthquake shakes Twitter users: real-time event detection by social sensors”, in Proc. of WWW’10, ACM, 2010, pp. 851-860. Google ScholarDigital Library
- M. Schinas, S. Papadopoulos, Y. Kompatsiaris, et al., “Visual event summarization on social media using topic modelling and graph-based ranking algorithms,” in Proc. of ICMR’15, ACM, 2015, pp. 203-210. Google ScholarDigital Library
- M. Schinas, S. Papadopoulos, Y. Kompatsiaris, et al., “StreamGrid: Summarization of Large Scale Events using Topic Modelling and Temporal Analysis,” SoMuS@ ICMR, 2014.Google Scholar
- X. Shang, H. Zhang, T S. Chua, “Deep learning generic features for cross-media retrieval,” International Conference on Multimedia Modeling. Springer International Publishing, 2016, pp. 264-275. Google ScholarDigital Library
- C. Shen, F. Liu, F. Weng, et al., “A Participant-based Approach for Event Summarization Using Twitter Streams,” HLT-NAACL, 2013, pp. 1152-1162.Google Scholar
- J. Song J, Y. Yang, Y. Yang, et al., “Inter-media hashing for large-scale retrieval from heterogeneous data sources,” in Proc. of SIGMOD’13. ACM, 2013, pp. 785-796. Google ScholarDigital Library
- S. Tang, F. Wu, S. Li, et al., “Sketch the Storyline with CHARCOAL: A Non-Parametric Approach,” IJCAI, 2015, pp. 3841-3848. Google ScholarDigital Library
- D. Wang, T. Li, and M. Ogihara, “Generating Pictorial Storylines Via Minimum-Weight Connected Dominating Set Approximation in Multi-View Graphs”, in Proc. of AAAI’12, 2012. Google ScholarDigital Library
- W. Wang, et al., “Effective deep learning-based multi-modal retrieval,” The VLDB Journal, vol. 25, no. 1, pp. 79-101, 2016. Google ScholarDigital Library
- Y. Wei, Y. Zhao, Z. Zhu, et al., “Modality-dependent cross-media retrieval,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 7, no. 4, pp. 57, 2016. Google ScholarDigital Library
- A. Weiler, M H. Scholl, F. Wanner, et al., “Event identification for local areas using social media streaming data,” in Proc. of the ACM SIGMOD Workshop on Databases and Social Networks. ACM, 2013, pp. 1-6. Google ScholarDigital Library
- A. Witayangkurn, T. Horanont, Y. Sekimoto, et al., “Anomalous event detection on large-scale gps data from mobile phones using hidden markov model and cloud platform,” in Proc. of UbiComp’13. ACM, 2013, pp. 1219-1228. Google ScholarDigital Library
- F. Wu, X. Lu, Z. Zhang, et al., “Cross-media semantic representation via bi-directional learning to rank,” in Proc. of MM’13, ACM, 2013, pp. 877-886. Google ScholarDigital Library
- D. Wu, Q. Liu, Y. Li, et al., “Adaptive Lookup of Open WiFi Using Crowdsensing,” IEEE/ACM Transactions on Networking, vol. 24, no. 6, pp. 3634-3647, 2016. Google ScholarDigital Library
- J. Xu, T C. Lu, “Seeing the big picture from microblogs: Harnessing social signals for visual event summarization,” in Proc. of IUI’15. ACM, 2015, pp. 62-66. Google ScholarDigital Library
- Z. Yu, F. Wu, Y. Yang, et al., “Discriminative coupled dictionary hashing for fast cross-media retrieval,” in Proc. of SIGIR’14, ACM, 2014, pp. 395-404. Google ScholarDigital Library
- D. Zhang and W.J. Li, “Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization,” in Proc. of AAAI’14, 2014. Google ScholarDigital Library
- Q. Zhang, B. Goncalves, “Topical differences between Chinese language Twitter and Sina Weibo,” in Proc. of WWW’16, 2016. Google ScholarDigital Library
- J. Zhou, G. Ding, Y. Guo, “Latent semantic sparse hashing for cross-modal similarity search,” in Proc. of SIGIR’14, 2014, pp. 415-424. Google ScholarDigital Library
- W. Zhou, et al., “Generating textual storyline to improve situation awareness in disaster management,” in Proc. IRI’14, 2014, pp. 585-592.Google ScholarCross Ref
- L. J. Griffin, “Narrative, event-structure analysis, and causal interpretation in historical sociology,” American journal of Sociology, vol. 98, no. 5, pp. 1094-1133, 1993.Google ScholarCross Ref
Recommendations
CrowdStory: multi-layered event storyline generation with mobile crowdsourced data
UbiComp '16: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: AdjunctOnline social media, like Twitter, can be viewed as a kind of source of mobile crowdsourced data. It can be utilized to understand real-world social events. Recently, many researchers have worked on event summarization from this kind of data. However, ...
FBSN: A hybrid fine-grained neural network for biomedical event trigger identification
AbstractBiomedical event extraction is one of the fundamental tasks in medical research and disease prevention. Event trigger usually signifies the occurrence of a biomedical event by adopting a word or a phrase. Meanwhile, the task of ...
Sentiment evaluation of forex news
CF '19: Proceedings of the 16th ACM International Conference on Computing FrontiersSentiment analysis is significant for excavating text opinion. There are two issues in the foreign exchange (Forex) field. 1) In sentiment orientation, most researches focus on product reviews, lack fine-grained sentiment analysis for Forex news. 2) In ...
Comments