24,663 Hits in 2.9 sec

Detecting Real-World Influence through Twitter

Jean-Valere Cossu, Nicolas Dugue, Vincent Labatut
2015 2015 Second European Network Intelligence Conference  
In this paper, we investigate the issue of detecting the real-life influence of people based on their Twitter account.  ...  We thus propose several Machine Learning approaches based on Natural Language Processing and Social Network Analysis to label Twitter users as Influencers or not.  ...  These users were annotated according to their perceived real-world (offline) influence, and not by considering specifically their Twitter account.  ... 
doi:10.1109/enic.2015.20 dblp:conf/enic/CossuDL15 fatcat:2zh7xm5ltjgnvoszcmax3tzqh4

Real World City Event Extraction from Twitter Data Streams

Yuchao Zhou, Suparna De, Klaus Moessner
2016 Procedia Computer Science  
In this work, we propose a novel unsupervised method to extract real world events that may impact city services such as traffic, public transport, public safety etc., from Twitter streams.  ...  We apply our developed approach to a real world dataset of tweets collected from the city of London.  ...  TwitterStand 6 provides an online clustering and classification method to detect news as reported by Twitter users , however, the detected news cannot be directly linked to real world events.  ... 
doi:10.1016/j.procs.2016.09.069 fatcat:kiha4ppferefpmfj6ubxyjafqu

The central community of Twitter ego-networks as a means for fake influencer detection

Nicolas Tsapatsoulis, Vasiliki Anastasopoulou, Klimis Ntalianis
2019 Zenodo  
We show that the central community of egocentric social media networks, such as the ego networks on Twitter and Instagram, tell us much more about the actual influence of the ego than the whole egocentric  ...  The central community of social networks, usually represented through the highest degree k-core of the corresponding graph, is proposed here as a compact representation of large social networks.  ...  As already explained our method emphasises on the identifi-cation of the central community of real-world large ecocentric networks mined from the Twitter.  ... 
doi:10.5281/zenodo.3237771 fatcat:jaqtzoaphvak7mkiiup2ga5e7m

Advanced Characteristic Analysis of Real Time Junk Occurrences in Twitter

Ancy S, Aruna Jasmine.J
2018 International Journal of Computer Applications Technology and Research  
The results show that our proposed NLTK can remarkably improve the spam detection accuracy in real-world scenario  ...  Spam on twitter is a major threat in recent days. To overcome these problems we take many steps to work on this. This work uses twitter as the input data source to address the problem of real-time.  ...  Through our evaluations, we show that this proposed NLTK can effectively detect Twitter spam by cutting down the influence of "Spam Drift" issue.  ... 
doi:10.7753/ijcatr0712.1001 fatcat:3aknsycxardtbdvp2umy6wdja4

SIDEWAYS-2022 @ HT-2022: 7th International Workshop on Social Media World Sensors

Mario Cataldi, Luigi Di Caro, Claudio Schifanella
2022 7th International Workshop on Social Media World Sensors  
This long-running workshop aims at focusing the attention on a particular perspective of these powerful communication channels, which is that of social sensors, where each user reacts in real time to the  ...  Technologies and AI artifacts may support automatic or semiautomatic applications for information detection and integration, offering sideways to the existing authoritative information media and the information  ...  For this, while many contents are not specifically related to any particular real-world event, informative event messages nevertheless abound.  ... 
doi:10.1145/3544795.3544844 fatcat:vmuhgybz2vedzgj5kf6dvxypge


Prateek Dewan, Mayank Gupta, Kanika Goyal, Ponnurangam Kumaraguru
2013 Proceedings of the 5th IBM Collaborative Academia Research Exchange Workshop on - I-CARE '13  
Facebook, Twitter, Google+, YouTube, and Flickr, and presents real-time analytics and visualizations.  ...  However, most of the work has focused on utilizing a single social network for monitoring such events, mostly Twitter.  ...  The goal of MultiOSN is to provide a platform for data collection, analysis, and visualization during real-world events, and help us to fill the gaps in the existing research work on studying real-world  ... 
doi:10.1145/2528228.2528235 fatcat:vbnsqbeupnalte6xx3icmdrxku

Vulnerability Disclosure in the Age of Social Media: Exploiting Twitter for Predicting Real-World Exploits

Carl Sabottke, Octavian Suciu, Tudor Dumitras
2015 USENIX Security Symposium  
world.  ...  We conduct a quantitative and qualitative exploration of the vulnerability-related information disseminated on Twitter.  ...  In the security domain, much attention has been focused on detecting Twitter spam accounts [57] and detecting malicious uses of Twitter aimed at gaining political influence [30, 52, 55] .  ... 
dblp:conf/uss/SabottkeSD15 fatcat:shbbr2ftsvh5blt7tcst5jdqdq

Traffic event detection framework using social media

A. Salas, P. Georgakis, C. Nwagboso, A. Ammari, I. Petalas
2017 2017 IEEE International Conference on Smart Grid and Smart Cities (ICSGSC)  
Twitter has been used as a way of predicting revenues, accidents, natural disasters, and traffic. This paper proposes a framework for the real-time detection of traffic events using Twitter data.  ...  In recent years, there has been an increasing interest in Twitter because of the real-time nature of its data.  ...  As a result, several authors have studied the influence of Twitter at predicting real-world outcomes such as revenues, accidents, natural disasters and traffic.  ... 
doi:10.1109/icsgsc.2017.8038595 fatcat:o5b5jzzexrdulmrf4grmo4xsii


S. Xu, S. Li, R. Wen, W. Huang
2019 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Compared with hourly average travel speed data, 81% of detected events were identified as real-world traffic events.  ...  A case study was conducted in Toronto, Canada using Twitter data.  ...  By validating with the hourly average travel speed data through a Z-test, 81% of the detected events can be identified as actual real-world traffic events when the significance level was set as 0.1.  ... 
doi:10.5194/isprs-annals-iv-2-w5-543-2019 fatcat:7mszuuasareypnxy5lnszcerlm

SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection [article]

Shangbin Feng, Herun Wan, Ningnan Wang, Jundong Li, Minnan Luo
2021 arXiv   pre-print
As a result, they fail to generalize to real-world scenarios on the Twittersphere where different types of bots co-exist. Additionally, bots in Twitter are constantly evolving to evade detection.  ...  SATAR is also proved to generalize in real-world scenarios and adapt to evolving generations of social media bots.  ...  real-world datasets to evaluate SATAR and competitive baselines.  ... 
arXiv:2106.13089v2 fatcat:lybltfco6zfwlhednpb5upqn3u

A survey of researching on micro-blogging [chapter]

Lei-Na Ji, Wei-Jiang Li, Hui Deng, Feng Wang
2013 Environment, Energy and Sustainable Development  
According to relevant public data, the earliest and most famous micro-blogging --Twitter already has 500 million registered users in the world.  ...  It can be used to share, disseminate and obtain all kinds of real-time updated information with about 140 words.  ...  RELATED WORK Millions of people around the world use Twitter to remain social connections to their friends, family members and co-workers through their computers and mobile phones [4] .  ... 
doi:10.1201/b16320-214 fatcat:lmfpmdwoabdfnoqqxb45qw3bqq

Detecting and Tracking Significant Events for Individuals on Twitter by Monitoring the Evolution of Twitter Followership Networks

Tao Tang, Guangmin Hu
2020 Information  
Abundant user-generated content makes Twitter become one of the major channels for people to obtain information about real-world events.  ...  Event detection techniques help to extract events from massive amounts of Twitter data.  ...  We list the detected PIEs and the real-world events in Table 1 according to the dates. Table 1. The correspondent relationship between Personal Important Events (PIEs) and real-world events.  ... 
doi:10.3390/info11090450 fatcat:y54iv6gzuvbbng7us3dnzk3fn4

Evidential Independence Maximization on Twitter Network [chapter]

Siwar Jendoubi, Mouna Chebbah, Arnaud Martin
2018 Lecture Notes in Computer Science  
The proposed approach is experimented on real data crawled from Twitter.  ...  Detecting independent users is interesting because a part of them can be influencers. Independent users that are not influencers can be directly targeted as they cannot be influenced.  ...  Next, we experiment the proposed solution on real world data collected from Twitter and we study the quality of selected users according to their #Mention, #Retweet, #Tweet and #Citation.  ... 
doi:10.1007/978-3-319-99383-6_16 fatcat:jfccu6ciejd5bkhc2vt45wuboy

U-Tool: A Urban-Toolkit for Enhancing City Maps Through Citizens' Activity [chapter]

Elena del Val, Javier Palanca, Miguel Rebollo
2016 Lecture Notes in Computer Science  
Access to information is done through the public API for developers of Twitter and Instagram.  ...  Twitter, through the application Twitter Analytics, provides users with statistics of their activity and the impact it has on their friendship circles.  ... 
doi:10.1007/978-3-319-39324-7_22 fatcat:s2fok2wpubfkndyjqfr2s37ylu

Event-Radar: Real-time Local Event Detection System for Geo-Tagged Tweet Streams [article]

Sibo Zhang, Yuan Cheng, Deyuan Ke
2017 arXiv   pre-print
A robust and efficient cloud-based real-time local event detection software system would benefit various aspects in the real-life society, from shopping recommendation for customer service providers to  ...  We use the preliminary research GeoBurst as a starting point, which proposed a novel method to detect local events.  ...  Real-world event identification on Twitter [38] used an online clustering technique to associate tweets with the real-world event.  ... 
arXiv:1708.05878v2 fatcat:xbbluu3sg5b2dhe4zlkbfsmbme
« Previous Showing results 1 — 15 out of 24,663 results