Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImage Analysis Enhanced Event Detection from Geo-tagged Tweet Streams
72
0
0.0
(
0
)
Added by
Yi Han
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Events detected from social media streams often include early signs of accidents, crimes or disasters. Therefore, they can be used by related parties for timely and efficient response. Although significant progress has been made on event detection from tweet streams, most existing methods have not considered the posted images in tweets, which provide richer information than the text, and potentially can be a reliable indicator of whether an event occurs or not. In this paper, we design an event detection algorithm that combines textual, statistical and image information, following an unsupervised machine learning approach. Specifically, the algorithm starts with semantic and statistical analyses to obtain a list of tweet clusters, each of which corresponds to an event candidate, and then performs image analysis to separate events from non-events---a convolutional autoencoder is trained for each cluster as an anomaly detector, where a part of the images are used as the training data and the remaining images are used as the test instances. Our experiments on multiple datasets verify that when an event occurs, the mean reconstruction errors of the training and test images are much closer, compared with the case where the candidate is a non-event cluster. Based on this finding, the algorithm rejects a candidate if the difference is larger than a threshold. Experimental results over millions of tweets demonstrate that this image analysis enhanced approach can significantly increase the precision with minimum impact on the recall.
rate research
Read More
A common goal in network modeling is to uncover the latent community structure present among nodes. For many real-world networks, observed connections consist of events arriving as streams, which are then aggregated to form edges, ignoring the temporal dynamic component. A natural way to take account of this temporal dynamic component of interactions is to use point processes as the foundation of the network models for community detection. Computational complexity hampers the scalability of such approaches to large sparse networks. To circumvent this challenge, we propose a fast online variational inference algorithm for learning the community structure underlying dynamic event arrivals on a network using continuous-time point process latent network models. We provide regret bounds on the loss function of this procedure, giving theoretical guarantees on performance. The proposed algorithm is illustrated, using both simulation studies and real data, to have comparable performance in terms of community structure in terms of community recovery to non-online variants. Our proposed framework can also be readily modified to incorporate other popular network structures.
Geo-tagged tweets can potentially help with sensing the interaction of people with their surrounding environment. Based on this hypothesis, this paper makes use of geotagged tweets in order to ascertain various land uses with a broader goal to help with urban/city planning. The proposed method utilises supervised learning to reveal spatial land use within cities with the help of Twitter activity signatures. Specifically, the technique involves using tweets from three cities of Australia namely Brisbane, Melbourne and Sydney. Analytical results are checked against the zoning data provided by respective city councils and a good match is observed between the predicted land use and existing land zoning by the city councils. We show that geo-tagged tweets contain features that can be useful for land use identification.
Camera geo-localization from a monocular video is a fundamental task for video analysis and autonomous navigation. Although 3D reconstruction is a key technique to obtain camera poses, monocular 3D reconstruction in a large environment tends to result in the accumulation of errors in rotation, translation, and especially in scale: a problem known as scale drift. To overcome these errors, we propose a novel framework that integrates incremental structure from motion (SfM) and a scale drift correction method utilizing geo-tagged images, such as those provided by Google Street View. Our correction method begins by obtaining sparse 6-DoF correspondences between the reconstructed 3D map coordinate system and the world coordinate system, by using geo-tagged images. Then, it corrects scale drift by applying pose graph optimization over Sim(3) constraints and bundle adjustment. Experimental evaluations on large-scale datasets show that the proposed framework not only sufficiently corrects scale drift, but also achieves accurate geo-localization in a kilometer-scale environment.
Recent studies on human mobility show that human movements are not random and tend to be clustered. In this connection, the movements of Twitter users captured by geo-located tweets were found to follow similar patterns, where a few geographic locations dominate the tweeting activity of individual users. However, little is known about the semantics (landuse types) and temporal tweeting behavior at those frequently-visited locations. Furthermore, it is generally assumed that the top two visited locations for most of the users are home and work locales (Hypothesis A) and people tend to tweet at their top locations during a particular time of the day (Hypothesis B). In this paper, we tested these two frequently cited hypotheses by examining the tweeting patterns of more than 164,000 unique Twitter users whom were residents of the city of Chicago during 2014. We extracted landuse attributes for each geo-located tweet from the detailed inventory of the Chicago Metropolitan Agency for Planning. Top-visited locations were identified by clustering semantic enriched tweets using a DBSCAN algorithm. Our results showed that although the top two locations are likely to be residential and occupational/educational, a portion of the users deviated from this case, suggesting that the first hypothesis oversimplify real-world situations. However, our observations indicated that people tweet at specific times and these temporal signatures are dependent on landuse types. We further discuss the implication of confounding variables, such as clustering algorithm parameters and relative accuracy of tweet coordinates, which are critical factors in any experimental design involving Twitter data.
Tweet classification has attracted considerable attention recently. Most of the existing work on tweet classification focuses on topic classification, which classifies tweets into several predefined categories, and sentiment classification, which classifies tweets into positive, negative and neutral. Since tweets are different from conventional text in that they generally are of limited length and contain informal, irregular or new words, so it is difficult to determine user intention to publish a tweet and user attitude towards certain topic. In this paper, we aim to simultaneously classify tweet purpose, i.e., the intention for user to publish a tweet, and position, i.e., supporting, opposing or being neutral to a given topic. By transforming this problem to a multi-label classification problem, a multi-label classification method with post-processing is proposed. Experiments on real-world data sets demonstrate the effectiveness of this method and the results outperform the individual classification methods.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
