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.
Many social media researchers and data scientists collected geo-tagged tweets to conduct spatial analysis or identify spatiotemporal patterns of filtered messages for specific topics or events. This paper provides a systematic view to illustrate the characteristics (data noises, user biases, and system errors) of geo-tagged tweets from the Twitter Streaming API. First, we found that a small percentage (1%) of active Twitter users can create a large portion (16%) of geo-tagged tweets. Second, there is a significant amount (57.3%) of geo-tagged tweets located outside the Twitter Streaming API's …
Compared with traditional news media, social media nowadays provides a richer and more timely source of news. We are interested in multi-spatial level event detection from geo-tagged tweet streams. Specifically, in this paper we (1) examine the statistical characteristic for the time series of the number of geo-tagged tweets posted from specific regions during a short time interval, e.g., ten seconds or one minute; (2) verify from over thirty datasets that while almost all such time series exhibit self-similarity, those that correspond to events, especially short-term and unplanned outbursts, …
As the COVID-19 pandemic swept over the world, people discussed facts, expressed opinions, and shared sentiments on social media. Since the reaction to COVID-19 in different locations may be tied to local cases, government regulations, healthcare resources and socioeconomic factors, we curated a large geo-tagged Twitter dataset and performed exploratory analysis by location. Specifically, we collected 650,563 unique geo-tagged tweets across the United States (50 states and Washington, D.C.) covering the date range from January 25 to May 10, 2020. Tweet locations enabled us to conduct region-sp…
This paper introduces a spatiotemporal analysis framework for estimating hourly changing population distribution in urban areas using geo-tagged tweets (the messages containing users' physical locations), land use data, and dasymetric maps. We collected geo-tagged social media (tweets) within the County of San Diego during one year (2015) by using Twitter's Streaming Application Programming Interfaces (APIs). A semi-manual Twitter content verification procedure for data cleaning was applied first to separate tweets created by humans and non-human users (bots). The next step is to calculate the…
Geo-tagged Twitter data has been used recently to infer insights on the human aspects of social media. Insights related to demographics, spatial distribution of cultural activities, space-time travel trajectories for humans as well as happiness has been mined from geo-tagged twitter data in recent studies. To date, not much study has been done on the impact of the geolocation features of a Tweet on its sentiment. This observation has inspired us to propose the usage of geo-location features as a method to perform sentiment classification. In this method, the sentiment classification of geo-tag…
We observe and report on a systematic relationship between population density and Twitter use. Number of tweets, number of users and population per unit area are related by power laws, with exponents greater than one, that are consistent with each other and across a range of spatial scales. This implies that population density can accurately predict Twitter activity. Furthermore this trend can be used to identify `anomalous' areas that deviate from the trend. Analysis of geo-tagged and place-tagged tweets show that geo-tagged tweets are different with respect to user type and content. Our find…
Recent outbreaks of Ebola and Dengue viruses have again elevated the significance of the capability to quickly predict disease spread in an emergent situation. However, existing approaches usually rely heavily on the time-consuming census processes, or the privacy-sensitive call logs, leading to their unresponsive nature when facing the abruptly changing dynamics in the event of an outbreak. In this paper we study the feasibility of using large-scale Twitter data as a proxy of human mobility to model and predict disease spread. We report that for Australia, Twitter users' distribution correlat…
In this paper, we present quantitative and qualitative analysis of the top retweeted tweets (viral tweets) pertaining to the US presidential elections from September 1, 2016 to Election Day on November 8, 2016. For everyday, we tagged the top 50 most retweeted tweets as supporting or attacking either candidate or as neutral/irrelevant. Then we analyzed the tweets in each class for: general trends and statistics; the most frequently used hashtags, terms, and locations; the most retweeted accounts and tweets; and the most shared news and links. In all we analyzed the 3,450 most viral tweets that…
In current study, a mechanism to extract traffic related information such as congestion and incidents from textual data from the internet is proposed. The current source of data is Twitter. As the data being considered is extremely large in size automated models are developed to stream, download, and mine the data in real-time. Furthermore, if any tweet has traffic related information then the models should be able to infer and extract this data. Currently, the data is collected only for United States and a total of 120,000 geo-tagged traffic related tweets are extracted, while six million geo…
The tremendous popularity gained by Online Social Networks (OSNs) raises natural concerns about user privacy in social media platforms. Though users in OSNs can tune their privacy by deliberately deciding what to share, the interaction with other individuals within the social network can expose, and eventually disclose, sensitive information. Among all the sharable personal data, geo-location is particularly interesting. On one hand, users tend to consider their current location as a very sensitive information, avoiding to share it most of the time. On the other hand, service providers are int…
In this paper, we propose the design and implementation of the new geotagged media management system. A large amount of daily geo-tagged media data generated by user's smart phone, mobile device, dash cam and camera. Geotagged media, such as geovideos and geophotos, can be captured with spatial temporal information such as time, location, visible area, camera direction, moving direction and visible distance information. Due to the increase in geo-tagged multimedia data, the researches for efficient managing and mining geo-tagged multimedia are newly expected to be a new area in database and da…
DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio--textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not inc…
Social media platforms provide continuous access to user generated content that enables real-time monitoring of user behavior and of events. The geographical dimension of such user behavior and events has recently caught a lot of attention in several domains: mobility, humanitarian, or infrastructural. While resolving the location of a user can be straightforward, depending on the affordances of their device and/or of the application they are using, in most cases, locating a user demands a larger effort, such as exploiting textual features. On Twitter for instance, only 2% of all tweets are ge…
The location check-ins of users through various location-based services such as Foursquare, Twitter, and Facebook Places, etc., generate large traces of geo-tagged events. These event-traces often manifest in hidden (possibly overlapping) communities of users with similar interests. Inferring these implicit communities is crucial for forming user profiles for improvements in recommendation and prediction tasks. Given only time-stamped geo-tagged traces of users, can we find out these implicit communities, and characteristics of the underlying influence network? Can we use this network to impro…
With the rapid advancement of information and communication technologies, many researchers have adopted alternative data sources from private data vendors to study human movement dynamics in response to large-scale natural or societal events. Big geosocial data such as georeferenced tweets are publicly available and dynamically evolving as real-world events are happening, making it more likely to capture the real-time sentiments and responses of populations. However, precisely-geolocated geosocial data is scarce and biased toward urban population centers. In this research, we developed a big g…
University of California, Merced（加州大学默塞德分校）；University of Southern California（南加州大学）
This paper is the first work to perform spatio-temporal mapping of human activity using the visual content of geo-tagged videos. We utilize a recent deep-learning based video analysis framework, termed hidden two-stream networks, to recognize a range of activities in YouTube videos. This framework is efficient and can run in real time or faster which is important for recognizing events as they occur in streaming video or for reducing latency in analyzing already captured video. This is, in turn, important for using video in smart-city applications. We perform a series of experiments to show ou…
State Key Lab of Software Development Environment, Beihang University（北京航空航天大学软件开发环境国家重点实验室）；School of Statistics, Capital University of Economics and Business（首都经济贸易大学统计学院）
Given the development and abundance of social media, studying the stance of social media users is a challenging and pressing issue. Social media users express their stance by posting tweets and retweeting. Therefore, the homogeneous relationship between users and the heterogeneous relationship between users and tweets are relevant for the stance detection task. Recently, graph neural networks (GNNs) have developed rapidly and have been applied to social media research. In this paper, we crawl a large-scale dataset of the 2020 US presidential election and automatically label all users by manual…
The pervasiveness of mobile devices, which is increasing daily, is generating a vast amount of geo-located data allowing us to gain further insights into human behaviors. In particular, this new technology enables users to communicate through mobile social media applications, such as Twitter, anytime and anywhere. Thus, geo-located tweets offer the possibility to carry out in-depth studies on human mobility. In this paper, we study the use of Twitter in transportation by identifying tweets posted from roads and rails in Europe between September 2012 and November 2013. We compute the percentage…
In this work, we propose a novel technique to determine the aesthetic score of a location from social metadata of Flickr photos. In particular, we built machine learning classifiers to predict the class of a location where each class corresponds to a set of locations having equal aesthetic rating. These models are trained on two empirically build datasets containing locations in two different cities (Rome and Paris) where aesthetic ratings of locations were gathered from TripAdvisor.com. In this work we exploit the idea that in a location with higher aesthetic rating, it is more likely for an …
University Politehnica of Bucharest（布加勒斯特理工大学）；Fraunhofer Institute for Open Communication Systems（弗劳恩霍夫开放通信系统研究所）
Real-time social media data can provide useful information on evolving hazards. Alongside traditional methods of disaster detection, the integration of social media data can considerably enhance disaster management. In this paper, we investigate the problem of detecting geolocation-content communities on Twitter and propose a novel distributed system that provides in near real-time information on hazard-related events and their evolution. We show that content-based community analysis leads to better and faster dissemination of reports on hazards. Our distributed disaster reporting system analy…
Many real world systems or web services can be represented as a network such as social networks and transportation networks. In the past decade, many algorithms have been developed to detect the communities in a network using connections between nodes. However in many real world networks, the locations of nodes have great influence on the community structure. For example, in a social network, more connections are established between geographically proximate users. The impact of locations on community has not been fully investigated by the research literature. In this paper, we propose a commun…
The rise in popularity and ubiquity of Twitter has made sentiment analysis of tweets an important and well-covered area of research. However, the 140 character limit imposed on tweets makes it hard to use standard linguistic methods for sentiment classification. On the other hand, what tweets lack in structure they make up with sheer volume and rich metadata. This metadata includes geolocation, temporal and author information. We hypothesize that sentiment is dependent on all these contextual factors. Different locations, times and authors have different emotional valences. In this paper, we e…
There is an increasing trend of people leaving digital traces through social media. This reality opens new horizons for urban studies. With this kind of data, researchers and urban planners can detect many aspects of how people live in cities and can also suggest how to transform cities into more efficient and smarter places to live in. In particular, their digital trails can be used to investigate tastes of individuals, and what attracts them to live in a particular city or to spend their vacation there. In this paper we propose an unconventional way to study how people experience the city, u…
With the rise of Social Media, people obtain and share information almost instantly on a 24/7 basis. Many research areas have tried to gain valuable insights from these large volumes of freely available user generated content. With the goal of extracting knowledge from social media streams that might be useful in the context of intelligent transportation systems and smart cities, we designed and developed a framework that provides functionalities for parallel collection of geo-located tweets from multiple pre-defined bounding boxes (cities or regions), including filtering of non-complying twee…
After George Floyd's death in May 2020, the volume of discussion in social media increased dramatically. A series of protests followed this tragic event, called as the 2020 BlackLivesMatter movement. Eventually, many user accounts are deleted by their owners or suspended due to violating the rules of social media platforms. In this study, we analyze what happened in Twitter before and after the event triggers with respect to deleted and suspended users. We create a novel dataset that includes approximately 500k users sharing 20m tweets, half of whom actively participated in the 2020 BlackLives…
Predicting investors reactions to financial and political news is important for the early detection of stock market jitters. Evidence from several recent studies suggests that online social media could improve prediction of stock market movements. However, utilizing such information to predict strong stock market fluctuations has not been explored so far. In this work, we propose a novel event detection method on Twitter, tailored to detect financial and political events that influence a specific stock market. The proposed approach applies a bursty topic detection method on a stream of tweets …
People's behavior on online social networks, which store geo-tagged information showing where people were or are at the moment, can provide information about their offline life as well. In this paper we present one possible research direction that can be taken using Flickr dataset of publicly available geo-tagged media objects (e.g., photographs, videos). Namely, our focus is on investigating attractiveness of countries or smaller large-scale composite regions (e.g., US states) for foreign visitors where attractiveness is defined as the absolute number of media objects taken in a certain state…
Event detection in a multimodal Twitter dataset is considered. We treat the hashtags in the dataset as instances with two modes: text and geolocation features. The text feature consists of a bag-of-words representation. The geolocation feature consists of geotags (i.e., geographical coordinates) of the tweets. Fusing the multimodal data we aim to detect, in terms of topic and geolocation, the interesting events and the associated hashtags. To this end, a generative latent variable model is assumed, and a generalized expectation-maximization (EM) algorithm is derived to learn the model paramete…
