Filters








1,744 Hits in 5.9 sec

Spatial Statistics of Term Co-occurrences for Location Prediction of Tweets [chapter]

Ozer Ozdikis, Heri Ramampiaro, Kjetil Nørvåg
2018 Lecture Notes in Computer Science  
We observe that using term pairs that spatially attract or repel each other yields significant increase in the accuracy of predicted locations.  ...  Predicting the locations of non-geotagged tweets is an active research area in geographical information retrieval.  ...  To the best of our knowledge, our work is the first to analyze spatial patterns of term co-occurrences with respect to the underlying term distributions, and use them in the location prediction of tweets  ... 
doi:10.1007/978-3-319-76941-7_37 fatcat:7lfg5fcv3ngolciwnydgqzxg6y

Estimating the Spatial Distribution of Crime Events around a Football Stadium from Georeferenced Tweets

Alina Ristea, Justin Kurland, Bernd Resch, Michael Leitner, Chad Langford
2018 ISPRS International Journal of Geo-Information  
of tweets for explaining the presence or absence of crime in the area around a football stadium on match days.  ...  Spatial clustering, spatial statistics, text mining as well as a hurdle negative binomial logistic regression for spatiotemporal explanations are utilized in our analysis.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijgi7020043 fatcat:cwdhzxdx2nc4pc2gavv423qaiq

A Survey on Content based Semantic Relations in Tweets

Alby Thomas, Sindhu L.
2015 International Journal of Computer Applications  
semantic information of tweets.  ...  Because of different writing conventions and character restriction there may be variation in the impact for the same event.  ...  And also term similarity scores are more better to extract the semantic relation among tweets instead of using word co-occurrence.  ... 
doi:10.5120/ijca2015907558 fatcat:x4o47glaerfzbel7flvp66udvm

How events unfold

Ting Hua, Liang Zhao, Feng Chen, Chang-Tien Lu, Naren Ramakrishnan
2016 SIGSPATIAL Special  
There has been significant recent interest in the application of social media analytics for spatiotemporal event mining. However, no structured survey exists to capture developments in this space.  ...  Three branches of research are summarized here-corresponding (resp.) to modeling the past, present, and future-information tracking and backward analysis, spatiotemporal event detection, and spatiotemporal  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA  ... 
doi:10.1145/2876480.2876485 fatcat:34dx66my65b4pobofkioeaqknm

Geo-spatial text-mining from Twitter – a feature space analysis with a view toward building classification in urban regions

Matthias Häberle, Martin Werner, Xiao Xiang Zhu
2019 European Journal of Remote Sensing  
In this work, we conduct a feature space analysis of geo-tagged Twitter text messages from the Los Angeles area and a geo-spatial text mining approach to classify buildings types into commercial and residential  ...  By the year 2050, it is expected that about 68% of global population will live in cities.  ...  In this paper, we want to concentrate on social media text for geo-located tweets.  ... 
doi:10.1080/22797254.2019.1586451 fatcat:akjw4aiazzezhdhez7unle627i

#StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs [article]

Yichao Zhou, Jyun-yu Jiang, Xiusi Chen, Wei Wang
2021 arXiv   pre-print
In other words, historical statistics of COVID-19, as well as the population mobility data, become the essential knowledge for monitoring the pandemic trend.  ...  to construct heterogeneous knowledge graphs based on the extracted events and relationships among them; (ii) time series prediction module to provide both short-term and long-term forecasts of the confirmed  ...  ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their helpful comments.  ... 
arXiv:2108.03670v1 fatcat:fa5ifyhn5bdzdo4igujrsxik6e

Twitter location (sometimes) matters: Exploring the relationship between georeferenced tweet content and nearby feature classes

Stefan Hahmann, Ross Purves, Dirk Burghardt
2014 Journal of Spatial Information Science  
For this purpose, we correlate tweet topics to areas. In doing so, classified points of interest from OpenStreetMap serve as validation points.  ...  In this paper, we investigate whether microblogging texts (tweets) produced on mobile devices are related to the geographical locations where they were posted.  ...  generated content for cartographic communication" (BU 2605/1-1).  ... 
doi:10.5311/josis.2014.9.185 fatcat:xzczt5eynvahhb7pkieji2cqp4

Event Identification in Social Networks [article]

Fattane Zarrinkalam, Ebrahim Bagheri
2016 arXiv   pre-print
Applying traditional methods for event detection which are often proposed for processing large, formal and structured documents, are less effective, due to the short length, noisiness and informality of  ...  This article provides an overview of the state of the art in event detection from social networks.  ...  [40] have constructed a co-occurrence graph of emerging terms selected based on both the frequency of their occurrence and the importance of the users.  ... 
arXiv:1606.08521v1 fatcat:wdrsmj33pjewpjzkqsvf3mheuu

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

Sibo Zhang, Yuan Cheng, Deyuan Ke
2017 arXiv   pre-print
Recent studies have demonstrated that the geo-tagged tweet stream serves as an unprecedentedly valuable source for local event detection.  ...  The local event detection is to use posting messages with geotags on social networks to reveal the related ongoing events and their locations.  ...  The paper considers the location statistics of tweets and classifies the location data to train a classifier for locating meaningful tweets.  ... 
arXiv:1708.05878v2 fatcat:xbbluu3sg5b2dhe4zlkbfsmbme

Mining microblogs to infer music artist similarity and cultural listening patterns

Markus Schedl, David Hauger
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
We propose and evaluate four co-occurrence-based methods to compute artist similarity scores.  ...  From two collections of several million microblogs, which we gathered over ten months, music-related information is extracted and statistically analyzed.  ...  Furthermore, each cluster is assigned a set of geographic locations using both spatial clues in the tweets themselves and explicit location information as indicated by the twitterers.  ... 
doi:10.1145/2187980.2188218 dblp:conf/www/SchedlH12 fatcat:5cyg6k6lt5eq3fs6lunu5tykea

Data Mining and Knowledge Discovery [chapter]

Chao Zhang, Jiawei Han
2021 The Urban Book Series  
We first describe traditional approaches to urban activity modeling, including pattern discovery methods and statistical models.  ...  The availability of massive social-sensing data provides a unique opportunity for understanding urban space in a data-driven manner and improving many urban computing applications, ranging from urban planning  ...  SVD and Tensor can effectively recover the co-occurrence matrices and tensor, but the raw co-occurrence seems a less effective measure for location and activity prediction.  ... 
doi:10.1007/978-981-15-8983-6_42 fatcat:gxnx3jgu4fcqvbieg3ltmdovk4

Geo-text data and data-driven geospatial semantics

Yingjie Hu
2018 Geography Compass  
These links can be geotags, such as geotagged tweets or geotagged Wikipedia pages, in which location coordinates are explicitly attached to texts.  ...  On the one hand, it is challenging to automatically process this kind of data due to the unstructured texts and the complex spatial footprints of some places.  ...  Michael Goodchild, and the anonymous reviewers for their constructive comments and suggestions.  ... 
doi:10.1111/gec3.12404 fatcat:nx6icoco5bhgrhpynd6x7dlx4q

Exploiting User and Venue Characteristics for Fine-Grained Tweet Geolocation

Wen-Haw Chong, Ee-Peng Lim
2018 ACM Transactions on Information Systems  
To avoid confusion with such works, we have not used the term prediction. Analogy to document retrieval.  ...  For more effective geolocation, we first study some useful characteristics of venues and users, namely, spatial homophily, spatial focus, and the availability of location history.  ...  For each venue in each run, we also compare the cosine similarities of neighbors and nonneighbors with the following ratio statistic: R(v) = exp −cos nnb (v) cos nb (v) , (1) where the exponential function  ... 
doi:10.1145/3156667 fatcat:zedpk34umva4peqnft3n56j5yq

Regionalization of Social Interactions and Points-of-Interest Location Prediction With Geosocial Data

Achilleas Psyllidis, Jie Yang, Alessandro Bozzon
2018 IEEE Access  
) in conjunction with contiguity-constrained hierarchical clustering, to identify homogeneous regions of social interaction in cities and, subsequently, estimate appropriate locations for new POIs.  ...  Drawing on the discovered regions, we build a Factorization Machine-based model to estimate appropriate locations for new POIs in different urban contexts.  ...  ACKNOWLEDGMENT The authors would like to thank Erik Boertjes for his help in visualizing the multi-dimensional clusters (regions) on the maps of the three case-study cities.  ... 
doi:10.1109/access.2018.2850062 fatcat:hnd7rpbhkzf3xmmcm5sowu4miq

Twitter as an indicator for whereabouts of people? Correlating Twitter with UK census data

Enrico Steiger, René Westerholt, Bernd Resch, Alexander Zipf
2015 Computers, Environment and Urban Systems  
We correlated observed tweet patterns with official census data for the case study of London in order to underline the significance and reliability of Twitter data.  ...  Thus, the spatiotemporal analysis of Location Based Social Networks (LBSN) has great potential regarding the ability to sense spatial processes and to gain knowledge about urban dynamics, especially with  ...  We also thank the British Office for National Statistics for publishing UK Census data licensed under the Open Government License v. 2.0.  ... 
doi:10.1016/j.compenvurbsys.2015.09.007 fatcat:by53wwwhwzb2bouay6hafp5fdu
« Previous Showing results 1 — 15 out of 1,744 results