Filters








36 Hits in 1.8 sec

SEDTWik: Segmentation-based Event Detection from Tweets Using Wikipedia

Keval Morabia, Lalita Bhanu Murthy Neti, Aruna Malapati, Surender Singh Samant
2019 North American Chapter of the Association for Computational Linguistics  
This paper presents the problems associated with event detection from tweets and a tweet-segmentation based system for event detection called SEDTWik, an extension to a previous work, that is able to detect  ...  Previous works on event detection from tweets are either applicable to detect localized events or breaking news only or miss out on many important events.  ...  Aixin Sun, Associate Professor at Nanyang Technological University (NTU), Singapore for providing the Wikipedia keyphraseness values Q(s) that was used in calculating segment newsworthiness in subsection  ... 
doi:10.18653/v1/n19-3011 dblp:conf/naacl/MorabiaNMS19 fatcat:alrj3djrfjdaxh5tf23yjvxunu

Twevent

Chenliang Li, Aixin Sun, Anwitaman Datta
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In this paper, we propose a segment-based event detection system for tweets, called Twevent.  ...  We also show that Twevent is efficient and scalable, leading to a desirable solution for event detection from tweets.  ...  Overview of Twevent To address the above challenges, we present Twevent, a novel segment-based event detection system for tweets.  ... 
doi:10.1145/2396761.2396785 dblp:conf/cikm/LiSD12 fatcat:ro67eohxsrd5rdzyfxkzytjeta

Frame-Based Representation for Event Detection on Twitter

Yanxia QIN, Yue ZHANG, Min ZHANG, Dequan ZHENG
2018 IEICE transactions on information and systems  
Experimental results show that frame-based event detection leads to improved precision over a state-of-the-art baseline segment-based event detection method.  ...  Large scale first-hand tweets motivate automatic event detection on Twitter. Previous approaches model events by clustering tweets, words or segments.  ...  The proposed Frame based representation for Event Detection on Twitter, FrED, outperforms the segment-based method of Li et al. [6] (Twevent) on a benchmark of 31 million tweets.  ... 
doi:10.1587/transinf.2017edp7311 fatcat:hrmaqt6t3zechot3q3sbh5uchy

MaTED: Metadata-Assisted Twitter Event Detection System [chapter]

Abhinay Pandya, Mourad Oussalah, Panos Kostakos, Ummul Fatima
2020 Communications in Computer and Information Science  
We extend this line of research by incorporating external knowledge bases such as DBPedia, WordNet; and exploiting specific features of Twitter for efficient event detection.  ...  Existing approaches for event detection have mainly focused on building a temporal profile of named entities and detecting unusually large bursts in their usage to signify an event.  ...  This work is partly supported by EU YoungRes project (#823701) on polarization detection.  ... 
doi:10.1007/978-3-030-50146-4_30 fatcat:6sqihime7vdbnn5j7pvvldnlza

TopicSketch: Real-Time Bursty Topic Detection from Twitter

Wei Xie, Feida Zhu, Jing Jiang, Ee-Peng Lim, Ke Wang
2013 2013 IEEE 13th International Conference on Data Mining  
A bursty topic in Twitter is one that triggers a surge of relevant tweets within a short time, which often reflects important events of mass interest.  ...  Especially it is also demonstrated that TopicSketch can potentially handle hundreds of millions tweets per day which is close to the total number of daily tweets in Twitter and present bursty event in  ...  Twevent [20] is the state-of-the-art system detecting events from tweet stream.  ... 
doi:10.1109/icdm.2013.86 dblp:conf/icdm/XieZJLW13 fatcat:l474imet7fdsdnjh7mal3eg22m

Discovery of Newsworthy Events in Twitter

Fernando Fradique Duarte, Óscar Mortágua Pereira, Rui L. Aguiar
2018 Proceedings of the 3rd International Conference on Internet of Things, Big Data and Security  
One such research field is the field of event detection in Social Media. The purpose of this work is to implement a system to detect newsworthy events in Twitter.  ...  For this purpose, a segmentation algorithm implemented using a dynamic programming approach is proposed in order to split the tweets into segments.  ...  More closely related to this work, Twevent (C. Li et al. 2012 ) is proposed as a segment based event detection framework.  ... 
doi:10.5220/0006712702440252 dblp:conf/iotbd/DuartePA18 fatcat:gngvyn653jbmxcgcu4p7uaokbu

TopicSketch: Real-Time Bursty Topic Detection from Twitter

Wei Xie, Feida Zhu, Jing Jiang, Ee-Peng Lim, Ke Wang
2016 IEEE Transactions on Knowledge and Data Engineering  
A bursty topic in Twitter is one that triggers a surge of relevant tweets within a short time, which often reflects important events of mass interest.  ...  Especially it is also demonstrated that TopicSketch can potentially handle hundreds of millions tweets per day which is close to the total number of daily tweets in Twitter and present bursty event in  ...  Twevent [20] is the state-of-the-art system detecting events from tweet stream.  ... 
doi:10.1109/tkde.2016.2556661 fatcat:3obzc5w7wfd3ffmno7z32fasqq

An Improved Approach for Twitter Data Analysis using Clustering and J48 Classification

Ravikant Choudhary, Deepak Sain
2016 International Journal of Computer Applications  
Social Media Network is one of the main source of data for various event detections.  ...  The Planned Procedure applied here is based on SVM Supervised Learning based Clustering of Similar features of Traffic and then classify the Data using J48 Decision Tree to classify number of events performed  ...  Li et al. present Twevent in [8] . It is a state-of-the-art system detecting events from the tweet stream.  ... 
doi:10.5120/ijca2016912562 fatcat:7wmupe3rs5gujgp44ve3h6hbeu

SMERC: Social media event response clustering using textual and temporal information [article]

Peter Mathews, Caitlin Gray, Lewis Mitchell, Giang T. Nguyen, Nigel G.Bean
2018 arXiv   pre-print
Tweet clustering for event detection is a powerful modern method to automate the real-time detection of events.  ...  Our method Social Media Event Response Clustering (SMERC) creates clusters of tweets based on their tendency to be related to a single event.  ...  Twevent [14] extracts continuous and non-overlapping word segments, and then calculates bursty event segments within a fixed length window.  ... 
arXiv:1811.05063v1 fatcat:2zgzzr56wbgzvj52t7uie65whm

Editorial: Survey and Experimental Analysis of Event Detection Techniques for Twitter

Andreas Weiler, Michael Grossniklaus, Marc H. Scholl
2016 Computer journal  
In response to this trend, numerous event detection techniques have been proposed to cope with the rate and volume of Twitter data streams.  ...  In this paper, we present a survey and experimental analysis of state-of-the-art event detection techniques for Twitter data streams.  ...  ACKNOWLEDGEMENTS We would also like to thank our students Christina Papavasileiou, Harry Schilling and Wai-Lok Cheung for their contributions to the implementations of the WATIS, EDCoW and ENB event detection  ... 
doi:10.1093/comjnl/bxw056 fatcat:3cndpwuqcjbypdpx6dxilrh5hy

Event Detection in Twitter by Weighting Tweet's Features [article]

Parinaz Rahimizadeh, Mohammad Javad Shayegan
2020 arXiv   pre-print
The main idea of this research is to differentiate among tweets based on some of their features.  ...  The results show that the average execution time and the precision of event detection in the presented method improved 27% and 31%, respectively, than the base method.  ...  In this method, events detected by matching the event's keywords on cluster labels. Li et al. (2012) have proposed a scalable segment-based event detection system, named Twevent.  ... 
arXiv:2010.00665v1 fatcat:rsd7vuwxwbd7xka2lbcditj7zi

Event Detection in Czech Twitter

Václav Rajtmajer, Pavel Král
2016 Research in Computing Science  
It uses user-lists to discover potentially interesting tweets which are further clustered into groups based on the content. The final decision is based on thresholding.  ...  The detected events are then presented to users in an acceptable form. A novel event detection approach adapted to the Czech Twitter is thus proposed.  ...  They propose a sophisticated system called Twevent, which first detects "bursty tweet segments" as event segments and then they are clustered considering both their frequency distribution and content similarity  ... 
doi:10.13053/rcs-110-1-7 fatcat:ce3ql4br5rdu3o2utjjb46x23q

PESTLE BASED EVENT DETECTION AND CLASSIFICATION

Vaishali Ugale .
2015 International Journal of Research in Engineering and Technology  
PESTLE based event detection approach proposed in this paper would help for PESTLE analysis of any organization.  ...  It helps to give true view of the environment from different aspects.  ...  A segment-based event detection system for tweets, called Twevent is discussed by Li et al. [16] .  ... 
doi:10.15623/ijret.2015.0405112 fatcat:r6lgqlle7baxfmqdp7jsgwsmkq

Detecting Events in Online Social Networks: Definitions, Trends and Challenges [chapter]

Nikolaos Panagiotou, Ioannis Katakis, Dimitrios Gunopulos
2016 Lecture Notes in Computer Science  
In this article, we present a wide range of event detection algorithms, architectures and evaluation methodologies.  ...  The problem of event detection has been examined in multiple social media sources like Twitter, Flickr, YouTube and Facebook.  ...  The TwEvent system [51] implements the idea of using tweet segments (Ngrams) instead of unigrams. Segment extraction is based on Wikipedia corpus and the Microsoft N-gram service 4 .  ... 
doi:10.1007/978-3-319-41706-6_2 fatcat:4neqe4dxlvczndld3d2xkqtyxu

Real-Time Data Harvesting Method for Czech Twitter

Pavel Král, Václav Rajtmajer
2017 Proceedings of the 9th International Conference on Agents and Artificial Intelligence  
This method uses user lists to discover potentially interesting tweets to download.  ...  The main goal is to propose an approach to harvest interesting messages from Twitter in Czech language with high download speed.  ...  The authors propose a system called Twevent, which first detects event segments and then, they are clustered considering both their frequency distribution and content similarity to discover events.  ... 
doi:10.5220/0006212402590265 dblp:conf/icaart/KralR17 fatcat:aa2lwi3yufam5ap2ehebyknswi
« Previous Showing results 1 — 15 out of 36 results