EventRadar: A Real-Time Local Event Detection Scheme Using Twitter Stream

Boettcher, Alexander; Lee, Dongman

doi:10.1109/greencom.2012.59

Cited by 60 publications

(32 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the increase of geo-tagged tweets, research efforts started to consider the spatial dimension of keywords, searching for localized events [4,19,22]. Since our objective is to conduct an online extraction of local keywords from a Twitter stream, we first review related work that tries to adopt an online extraction of keywords while ignoring the spatial dimension.…”

Section: Related Workmentioning

confidence: 99%

“…The topic of event detection from Twitter has recently received a considerable attention, e.g., [4,5,17,19], in particular feature-pivot detection, which detects the occurrence of events by clustering related keywords [2,5,7]. Due to the increase of geo-tagged tweets, research efforts started to consider the spatial dimension of keywords, searching for localized events [4,19,22].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On the locality of keywords in Twitter streams

Abdelhaq

Gertz

2014

Proceedings of the 5th ACM SIGSPATIAL International Workshop on GeoStreaming

View full text Add to dashboard Cite

The continuously increasing popularity of social media sites such as Twitter and Facebook has recently led to a number of approaches to detect and extract event information from social media streams. Such events play an important role, e.g., in supporting location-based services and improving situational awareness. Moreover, the introduction of GPSequipped communication devises has led to an increase in the percentage of geo-tagged messages. These help to detect localized events, i.e., events occurring at a certain location, such as sport events or accidents. The main entities that indicate a localized event are local keywords that exhibit a surge in usage at the event location.In this paper, we propose an approach to extract local keywords from a Twitter stream by (1) identifying local keywords, and (2) estimating the central location of each keyword. This extraction process is performed in an online fashion using a sliding window on the Twitter stream. In addition, we address the problem of spatial outliers that adversely affect a proper identification of local keywords. Outliers occur when people far away from an event location use related keywords in their Tweets. We handle this problem by adjusting the spatial distribution of keywords based on their co-occurrence with place names that may refer to the location of an event. We evaluate the performance of our framework to reliably and efficiently extracting local keywords and estimating their central locations using a Twitter dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

On the locality of keywords in Twitter streams

Abdelhaq

Gertz

2014

Proceedings of the 5th ACM SIGSPATIAL International Workshop on GeoStreaming

View full text Add to dashboard Cite

show abstract

“…They model the number of event-relevant tweets over time using a Poisson process and apply both particle and Kalman filters to estimate the location of detected events. Other efforts, e.g., [2,19] preserve the real-time processing of tweets and try to detect localized events. Our primary focus in this paper, however, is not to detect events but to continuously estimate fine-grained spatio-temporal information about bursty words, which in turn can be employed to build an event detection framework based on the feature-pivot paradigm [4].…”

Section: Related Workmentioning

confidence: 99%

“…Both geo-tagged and non-geo-tagged tweets are used in this step. (2) Estimating an initial spatial distribution over geographic space for each keyword using only geo-tagged tweets.…”

Section: Introductionmentioning

confidence: 99%

Spatio-temporal characteristics of bursty words in Twitter streams

Abdelhaq

Gertz

Sengstock

2013

Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Social networking and microblogging services such as Twitter provide a continuous source of data from which useful information can be extracted. The detection and characterization of bursty words play an important role in processing such data, as bursty words might hint to events or trending topics of social importance upon which actions can be triggered. While there are several approaches to extract bursty words from the content of messages, there is only little work that deals with the dynamics of continuous streams of messages, in particular messages that are geo-tagged.In this paper, we present a framework to identify bursty words from Twitter text streams and to describe such words in terms of their spatio-temporal characteristics. Using a time-aware word usage baseline, a sliding window approach over incoming tweets is proposed to identify words that satisfy some burstiness threshold. For these words then a timevarying, spatial signature is determined, which primarily relies on geo-tagged tweets. In order to deal with the noise and the sparsity of geo-tagged tweets, we propose a novel graph-based regularization procedure that uses spatial cooccurrences of bursty words and allows for computing sound spatial signatures. We evaluate the functionality of our online processing framework using two real-world Twitter datasets. The results show that our framework can efficiently and reliably extract bursty words and describe their spatio-temporal evolution over time.

show abstract

“…Sites like Twitter and Facebook act like social sensors facilitating the real time detection of disasters Vieweg et al, 2010) and local events (Boettcher and Lee, 2012;Lee and Sumiya, 2010). Relying on the real-time nature of Twitter and the volume of tweets around unusual or significant events, construct a real-time earthquake detection system using twitter users as sensors.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the third International Workshop on Natural Language Processing for Social Media

2015

View full text Add to dashboard Cite

It is our great pleasure to welcome you to the Third Workshop on Natural Language Processing for Social Media -SocialNLP'15, associated with NAACL 2015. SocialNLP is a new inter-disciplinary area of natural language processing (NLP) and social computing. There are three plausible directions of SocialNLP: (1) addressing issues in social computing using NLP techniques; (2) solving NLP problems using information from social media; and (3) handling new problems related to both social computing and natural language processing.Through this workshop, we anticipate to provide a platform for research outcome presentation and head-to-head discussion in the area of SocialNLP, with the hope to combine the insight and experience of prominent researchers from both NLP and social computing domains to contribute to the area of SocialNLP jointly. Also, selected and expanded versions of papers presented at SocialNLP will be published in two follow-on Special Issues of Springer Cognitive Computation (CogComp) and the International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP).The submissions to this year's workshop were again of high quality and we had a competitive selection process. We received 10 submissions from Asia, Europe, and the United States., and due to a rigorous review process, we only accepted 5 of them. Thus the acceptance rate was 50 percent. The workshop papers cover a broad range of SocialNLP-related topics, such as location name disambiguation, microblog and mobile game text processing, product mining, and social media user analysis. We had a total of 27 program committee members, and each submission is evaluated by at least 3 PC members. We warmly thank our PC members for the timely reviews and constructive comments.We are delighted to have two keynote speeches this year. Prof. Jacob Eisenstein, from Georgia Institute of Technology, will give a talk entitled "Variation and Change in Social Media Language"; Prof. Michael C. Frank, from Stanford University, will give a talk entitled "Predicting Pragmatic Reasoning about Language Use in Context". We also encourage attendees to attend the keynote talk presentations. These valuable and insightful talks can and will guide us to a better understanding of the future.Putting together SocialNLP 2015 was a team effort. We first thank the authors for providing the content of the program. We are grateful to the program committee members, who worked very hard in reviewing papers and providing feedback for authors. Finally, we especially thank the Workshop Committee Chairs Prof. Matt Post and Prof. Adam Lopez. Social media is sometimes described as a new domain, genre, or task for natural language processing. This suggests that it has specific properties that distinguish it from other sources of text. I will argue that there are exactly two such properties: variation and change. NLP research has historically focused on genres such as newstext, where there is strong pressure towards standardization. Far less pressure exists in social media, and...

show abstract

EventRadar: A Real-Time Local Event Detection Scheme Using Twitter Stream

Cited by 60 publications

References 9 publications

On the locality of keywords in Twitter streams

On the locality of keywords in Twitter streams

Spatio-temporal characteristics of bursty words in Twitter streams

Proceedings of the third International Workshop on Natural Language Processing for Social Media

Contact Info

Product

Resources

About