Real-Time Anomaly Detection and Popularity Prediction for Emerging Events on Twitter
Authors: 
Florian Steuber, Sinclair Schneider, João A. G. Schneider, Gabi Dreo RodosekAuthors Info & Claims
Florian Steuber, Sinclair Schneider, João A. G. Schneider, Gabi Dreo RodosekAuthors Info & ClaimsPages 300 - 304
Abstract
Due to their high volume and data recency, communications from social media platforms have become an excellent source for monitoring information diffusion. The insights leveraged are invaluable for social media analysts in the areas of event analysis and emergency management. Existing work ranges from the initial detection of incidents over information enrichment to determining an incident's relevance and life span. Until now, individual parts of this process have been considered separately, but never in combination.
In this work, we address this crucial need and present an approach for detecting the onset and context of emerging events and predicting their popularity two weeks after emergence on Twitter in real time. Our contribution is threefold. We first present an online learning anomaly detection method refined with temporal clustering to identify abnormal conversational volumes of keywords. Second, we reconstruct potentially underlying events causing the anomaly through the enrichment of contextual and temporal information. Third, we assess an event's relevance and life span by predicting the resonance corresponding tweets receive shortly after their publication.
References
[1]
S. Kumar, M. B. Khan, M. H. A. Hasanat, A. K. J. Saudagar, A. AlTameem, and M. AlKhathami, "An anomaly detection framework for twitter data,"
[2]
P. Anantharam, K. Thirunarayan, and A. Sheth, "Topical anomaly detection from twitter stream," in Proc. 4th Annu. ACM Web Sci. Conf. (WebSci), vol. 4, Jun. 22--24, 2012, pp. 11--14
[3]
S. Kumar, M. B. Khan, M. H. A. Hasanat, A. K. J. Saudagar, A. AlTameem, and M. AlKhathami, "An anomaly detection framework for twitter data," Appl. Sci., vol. 12, no. 21, Nov. 2022, Art. no. 11059
[4]
K. S. Karimi, A. Shakery, and R. M. Verma, "Enhancement of twitter event detection using news streams," Natural Lang. Eng., vol. 29, no. 2, Mar. 2023, pp. 181--200
[5]
J. Benhardus and J. Kalita, "Streaming trend detection in twitter," Int. J. Web Based Communities, vol. 9, no. 1, Jan. 2013, pp. 122--139
[6]
S. Hendrickson, J. Kolb, B. Lehman, and J. Montague, "Trend detection in social data," Twitter Inc. 2015. [Online]. Available: https://developer.twitter.com/content/dam/developer-twitter/pdfs-and-files/Trend-Detection.pdf
[7]
Twitter Inc. Anomaly Detection with R. GitHub. (2015). Accessed: May 05, 2023. [Online.] Available: https://github.com/twitter/AnomalyDetection
[8]
X. Hu et al., "Event detection in online social network: Methodologies, state-of-art, and evolution," Comput. Sci. Rev., vol. 46, Nov. 2022, Art. no. 100500, Appl. Sci., vol. 12, no. 21, Nov. 2022, Art. no. 11059.
[9]
C. T. Lo, Y. H. Lee, and J. H. Peng, "Real-time retweet count prediction using GNN model," in 9th Int. Conf. Appl. Syst. Innov. (ICASI), vol. 9, Apr. 21--25, 2023, pp. 181--183
[10]
J. Wang and Y. Yang, "Tweet Retweet Prediction Based on Deep Multitask Learning," Neural Process. Lett., vol. 54, no. 1, Feb. 2022, pp. 523--536
[11]
I. N. Lymperopoulos, "RC-Tweet: Modeling and predicting the popularity of tweets through the dynamics of a capacitor," Expert Syst. with Appl., vol. 163, Jan. 2021, Art. no. 113785
[12]
Y. Shang et al., "Popularity prediction of online contents via cascade graph and temporal information," Axioms, vol. 10, no. 3, Jul. 2021, Art. no. 159
[13]
J. Wen, Z. Zhang, Z. Yin, L. Sun, S. Su, and S. Y. Philip, "DeepBlue: Bi-layered LSTM for tweet popularity estimation," IEEE Trans. Knowl. and Data Eng., vol. 34, no. 10, Oct. 2022, pp. 4737--4752
[14]
R. O'Grady, "Times change and your data should too: The effect of training data recency on twitter classifiers," SANS Institute, White Paper, Jul. 2018. Accessed: Mar. 4, 2023. [Online]. Available: https://sansorg.egnyte.com/dl/mo5V4qRpDF
[15]
S. Sharma and V. Gupta, "Retweet prediction for large datasets of random tweets," in Proc. 2nd Int. Conf. Data Sci., Mach. Learn. and Appl. (ICDSMLA), A. Kumar, S. Senatore, and V. K. Gunjan, Eds. Nov. 21--22, 2022, pp. 665--673
[16]
B. Shulman, A. Sharma, and D. Cosley, "Predictability of popularity: Gaps between prediction and understanding," Proc. 10th Int. AAAI Conf. Web and Social Media (ICWSM), vol. 10, no. 1, May 17--20, 2016, pp. 348--357
[17]
Y. Zhang, M. Feng, K. Shang, Y. Ran, and C. J. Wang, "Peeking strategy for online news diffusion prediction via machine learning," Physica A: Statist. Mech. Appl., vol. 598, Jul. 2022, Art. no. 127357
[18]
R. M. Cao, X. F. Liu, and X. K. Xu, "Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes," R. Soc. Open Sci., vol. 8, no. 9, Sep. 2021, Art. no. 202245
[19]
C. H. Chee, J. Jaafar, I.A. Aziz, M.H. Hasan, & W. Yeoh, "Algorithms for frequent itemset mining: a literature review," Artificial Intelligence Review, 52, 2019, 2603--2621.
[20]
A. Lavin and S. Ahmad, "Evaluating real-time anomaly detection algorithms: The numenta anomaly benchmark," in IEEE 14th Int. Conf. Mach. Learn. and Appl. (ICMLA), Dec. 9--11. 2015, pp. 38--44
Index Terms
- Real-Time Anomaly Detection and Popularity Prediction for Emerging Events on Twitter
Index terms have been assigned to the content through auto-classification.
Recommendations
Discovering Emerging Topics in Social Streams via Link-Anomaly Detection
Detection of emerging topics is now receiving renewed interest motivated by the rapid growth of social networks. Conventional-term-frequency-based approaches may not be appropriate in this context, because the information exchanged in social-network ...
Celebrity's self-disclosure on Twitter and parasocial relationships
This study investigated how celebrities' self-disclosure on personal social media accounts, particularly Twitter, affects fans' perceptions. An online survey was utilized among a sample of 429 celebrity followers on Twitter. Results demonstrated that ...
Social Media Anomaly Detection: Challenges and Solutions
WSDM '17: Proceedings of the Tenth ACM International Conference on Web Search and Data MiningAnomaly detection is of critical importance to prevent malicious activities such as bullying, terrorist attack planning, and fraud information dissemination. With the recent popularity of social media, new types of anomalous behaviors arise, causing ...
Comments
Information & Contributors
Information
Published In
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 15 March 2024
Check for updates
Author Tags
Qualifiers
- Short-paper
Conference
ASONAM '23
Sponsor:
ASONAM '23: International Conference on Advances in Social Networks Analysis and Mining
November 6 - 9, 2023
Kusadasi, Turkiye
Acceptance Rates
ASONAM '23 Paper Acceptance Rate 53 of 145 submissions, 37%;
Overall Acceptance Rate 116 of 549 submissions, 21%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 168Total Downloads
- Downloads (Last 12 months)168
- Downloads (Last 6 weeks)23
Reflects downloads up to 14 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in