Event detection using Twitter: a spatio-temporal approach

Classification of Tweets Into Facts and Opinions Using Recurrent Neural Networks

In the last few years, the growth rate of the number of people who are active on Twitter has been consistently spiking. In India, even the government agencies have started using Twitter accounts as they feel that they can get connected to a greater number of people in a short span of time. Apart from the social media platforms, there are an enormous number of blogging applications that have popped up providing another platform for the people to share their views. With all this, the authenticity of the content that is being generated is going for a toss. On that note, the authors have the task in hand of differentiating the genuineness of the content. In this process, they have worked upon various techniques that would maximize the authenticity of the content and propose a long short-term memory (LSTM) model that will make a distinction between the tweets posted on the Twitter platform. The model in combination with the manually engineered features and the bag of words model is able to classify the tweets efficiently.

Changes in mobility amid the COVID-19 pandemic in Sapporo City, Japan: An investigation through the relationship between spatiotemporal population density and urban facilities

By the end of 2021, the Omicron variant of coronavirus disease 2019 had become the dominant cause of a worldwide pandemic crisis. This demands a deeper analysis to support policy makers in creating interventions that not only protect people from the pandemic but also remedy its negative effects on the economy. Thus, this study investigated people's mobility changes through the relationship between spatiotemporal population density and urban facilities. Results showed that places related to daily services, restaurants, commercial areas, and offices experienced decreased visits, with the highest decline belonging to commercial facilities. Visits to health care and production facilities were stable on weekdays but increased on holidays. Educational institutions' visits decreased on weekdays but increased on holidays. People's visits to residential housing and open spaces increased, with the rise in residential housing visits being more substantial. The results also confirmed that policy interventions (e.g., declaration of emergency and upgrade of restriction level) have a great impact on people's mobility in the short term. The findings would seem to indicate that visit patterns at service and restaurant places decreased least during the pandemic. The analysis outcomes suggest that policy makers should pay more attention to risk perception enhancement as a long-term measure. Furthermore, the study clarified the population density of each facility type in a time series. Improving model performance would be promising for tracking and predicting the spread of future pandemics.

Using social media in Kenya to quantify road safety: an analysis of novel data

BACKGROUND

Road traffic injuries are a large and growing cause of morbidity and mortality in low- and middle-income countries, especially in Africa. Systematic data collection for traffic incidents in Kenya is lacking and in many low- and middle-income countries available data sources are disparate or missing altogether. Many Kenyans use social media platforms, including Twitter; many road traffic incidents are publicly reported on the microblog platform. This study is a prospective cohort analysis of all tweets related to road traffic incidents in Kenya over a 24-month period (February 2019 to January 2021).

RESULTS

A substantial number of unique road incidents (3882) from across Kenya were recorded during the 24-month study period. The details available for each incident are widely variable, as reported and posted on Twitter. Particular times of day and days of the week had a higher incidence of reported road traffic incidents. A total of 2043 injuries and 1503 fatalities were recorded.

CONCLUSIONS

Twitter and other digital social media platforms can provide a novel source for road traffic incident and injury data in a low- and middle-income country. The data collected allows for the potential identification of local and national trends and provides opportunities to advocate for improved roadways and health systems for the emergent care from road traffic incidents and associated traumatic injuries.

Evaluating the usefulness of VGI from Waze for the reporting of flash floods

Using volunteered geographic information (VGI) to supplement disaster risk management systems, including forecasting, risk assessment, and disaster recovery, is increasingly popular. This attention is driven by difficulties in detection and characterization of hazards, as well as the rise of VGI appropriate for characterizing specific forms of risk. Flash-flood historical records, especially those that are impact-based, are not comprehensive, leading to additional barriers for flash-flood research and applications. In this paper we develop a method for associating VGI flood reporting clusters against authoritative data. Using Hurricane Harvey as a case study, VGI reports are assimilated into a spatial analytic framework that derives spatial and temporal clustering parameters supported by associations between Waze’s community-driven emergency operations center and authoritative reports. These parameters are then applied to find previously unreported likely flash flood-events. This study improves the understanding of the distribution of flash flooding during Hurricane Harvey and shows potential application to events in other areas where Waze data and reporting from official sources, such as the National Weather Service, are available.

MVGAN: Multi-View Graph Attention Network for Social Event Detection

Social networks are critical sources for event detection thanks to the characteristics of publicity and dissemination. Unfortunately, the randomness and semantic sparsity of the social network text bring significant challenges to the event detection task. In addition to text, time is another vital element in reflecting events since events are often followed for a while. Therefore, in this article, we propose a novel method named Multi-View Graph Attention Network (MVGAN) for event detection in social networks. It enriches event semantics through both neighbor aggregation and multi-view fusion in a heterogeneous social event graph. Specifically, we first construct a heterogeneous graph by adding the hashtag to associate the isolated short texts and describe events comprehensively. Then, we learn view-specific representations of events through graph convolutional networks from the perspectives of text semantics and time distribution, respectively. Finally, we design a hashtag-based multi-view graph attention mechanism to capture the intrinsic interaction across different views and integrate the feature representations to discover events. Extensive experiments on public benchmark datasets demonstrate that MVGAN performs favorably against many state-of-the-art social network event detection algorithms. It also proves that more meaningful signals can contribute to improving the event detection effect in social networks, such as published time and hashtags.

Detecting Urban Events by Considering Long Temporal Dependency of Sentiment Strength in Geotagged Social Media Data

The development of location-based services facilitates the use of location data for detecting urban events. Currently, most studies based on location data model the pattern of an urban dynamic and then extract the anomalies, which deviate significantly from the pattern as urban events. However, few studies have considered the long temporal dependency of sentiment strength in geotagged social media data, and thus it is difficult to further improve the reliability of detection results. In this paper, we combined a sentiment analysis method and long short-term memory neural network for detecting urban events with geotagged social media data. We first applied a dictionary-based method to evaluate the positive and negative sentiment strength. Based on long short-term memory neural network, the long temporal dependency of sentiment strength in geotagged social media data was constructed. By considering the long temporal dependency, daily positive and negative sentiment strength are predicted. We extracted anomalies that deviated significantly from the prediction as urban events. For each event, event-related information was obtained by analyzing social media texts. Our results indicate that the proposed approach is a cost-effective way to detect urban events, such as festivals, COVID-19-related events and traffic jams. In addition, compared to existing methods, we found that accounting for a long temporal dependency of sentiment strength can significantly improve the reliability of event detection.

Spatiotemporal data mining: a survey on challenges and open problems

Spatiotemporal data mining (STDM) discovers useful patterns from the dynamic interplay between space and time. Several available surveys capture STDM advances and report a wealth of important progress in this field. However, STDM challenges and problems are not thoroughly discussed and presented in articles of their own. We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM. We describe the challenging issues and their causes and open gaps of multiple STDM directions and aspects. Specifically, we investigate the challenging issues in regards to spatiotemporal relationships, interdisciplinarity, discretisation, and data characteristics. Moreover, we discuss the limitations in the literature and open research problems related to spatiotemporal data representations, modelling and visualisation, and comprehensiveness of approaches. We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks. We also highlight STDM issues related to multiple applications including crime and public safety, traffic and transportation, earth and environment monitoring, epidemiology, social media, and Internet of Things.

COVID-19 Discourse on Twitter in Four Asian Countries: Case Study of Risk Communication

BACKGROUND

COVID-19, caused by SARS-CoV-2, has led to a global pandemic. The World Health Organization has also declared an infodemic (ie, a plethora of information regarding COVID-19 containing both false and accurate information circulated on the internet). Hence, it has become critical to test the veracity of information shared online and analyze the evolution of discussed topics among citizens related to the pandemic.

OBJECTIVE

This research analyzes the public discourse on COVID-19. It characterizes risk communication patterns in four Asian countries with outbreaks at varying degrees of severity: South Korea, Iran, Vietnam, and India.

METHODS

We collected tweets on COVID-19 from four Asian countries in the early phase of the disease outbreak from January to March 2020. The data set was collected by relevant keywords in each language, as suggested by locals. We present a method to automatically extract a time-topic cohesive relationship in an unsupervised fashion based on natural language processing. The extracted topics were evaluated qualitatively based on their semantic meanings.

RESULTS

This research found that each government's official phases of the epidemic were not well aligned with the degree of public attention represented by the daily tweet counts. Inspired by the issue-attention cycle theory, the presented natural language processing model can identify meaningful transition phases in the discussed topics among citizens. The analysis revealed an inverse relationship between the tweet count and topic diversity.

CONCLUSIONS

This paper compares similarities and differences of pandemic-related social media discourse in Asian countries. We observed multiple prominent peaks in the daily tweet counts across all countries, indicating multiple issue-attention cycles. Our analysis identified which topics the public concentrated on; some of these topics were related to misinformation and hate speech. These findings and the ability to quickly identify key topics can empower global efforts to fight against an infodemic during a pandemic.

Multi-Class Imbalance in Text Classification: A Feature Engineering Approach to Detect Cyberbullying in Twitter

Twitter enables millions of active users to send and read concise messages on the internet every day. Yet some people use Twitter to propagate violent and threatening messages resulting in cyberbullying. Previous research has focused on whether cyberbullying behavior exists or not in a tweet (binary classification). In this research, we developed a model for detecting the severity of cyberbullying in a tweet. The developed model is a feature-based model that uses features from the content of a tweet, to develop a machine learning classifier for classifying the tweets as non-cyberbullied, and low, medium, or high-level cyberbullied tweets. In this study, we introduced pointwise semantic orientation as a new input feature along with utilizing predicted features (gender, age, and personality type) and Twitter API features. Results from experiments with our proposed framework in a multi-class setting are promising both with respect to Kappa (84%), classifier accuracy (93%), and F-measure (92%) metric. Overall, 40% of the classifiers increased performance in comparison with baseline approaches. Our analysis shows that features with the highest odd ratio: for detecting low-level severity include: age group between 19–22 years and users with <1 year of Twitter account activation; for medium-level severity: neuroticism, age group between 23–29 years, and being a Twitter user between one to two years; and for high-level severity: neuroticism and extraversion, and the number of times tweet has been favorited by other users. We believe that this research using a multi-class classification approach provides a step forward in identifying severity at different levels (low, medium, high) when the content of a tweet is classified as cyberbullied. Lastly, the current study only focused on the Twitter platform; other social network platforms can be investigated using the same approach to detect cyberbullying severity patterns.

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

People publish tweets on Twitter to share everything from global news to their daily life. 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. However, most existing techniques are based on Twitter information streams, which contain plenty of noise and polluted content that would affect the accuracy of the detecting result. In this article, we present an event discovery method based on the change of the user’s followers, which can detect the occurrences of significant events relevant to the particular user. We divide these events into categories according to the positive or negative effect on the specific user. Further, we observe the evolution of individuals’ followership networks and analyze the dynamics of networks. The results show that events have different effects on the evolution of different features of Twitter followership networks. Our findings may play an important role for realizing how patterns of social interaction are impacted by events and can be applied in fields such as public opinion monitoring, disaster warning, crisis management, and intelligent decision making.

Spatiotemporal Data Clustering: A Survey of Methods

Large quantities of spatiotemporal (ST) data can be easily collected from various domains such as transportation, social media analysis, crime analysis, and human mobility analysis. The development of ST data analysis methods can uncover potentially interesting and useful information. Due to the complexity of ST data and the diversity of objectives, a number of ST analysis methods exist, including but not limited to clustering, prediction, and change detection. As one of the most important methods, clustering has been widely used in many applications. It is a process of grouping data with similar spatial attributes, temporal attributes, or both, from which many significant events and regular phenomena can be discovered. In this paper, some representative ST clustering methods are reviewed, most of which are extended from spatial clustering. These methods are broadly divided into hypothesis testing-based methods and partitional clustering methods that have been applied differently in previous research. Research trends and the challenges of ST clustering are also discussed.

Space-time clusters and co-occurrence of chikungunya and dengue fever in Colombia from 2015 to 2016

Vector-borne diseases (VBDs) infect over one billion people and are responsible for over one million deaths each year, globally. Chikungunya (CHIK) and Dengue Fever (DENF) are emerging VBDs due to overpopulation, increases in urbanization, climate change, and other factors. Colombia has recently experienced severe outbreaks of CHIK AND DENF. Both viruses are transmitted by the Aedes mosquitoes and are preventable with a variety of surveillance and vector control measures (e.g. insecticides, reduction of open containers, etc.). Spatiotemporal statistics can facilitate the surveillance of VBD outbreaks by informing public health officials where to allocate resources to mitigate future outbreaks. We utilize the univariate Kulldorff space-time scan statistic (STSS) to identify and compare statistically significant space-time clusters of CHIK and DENF in Colombia during the outbreaks of 2015 and 2016. We also utilize the multivariate STSS to examine co-occurrences (simultaneous excess incidences) of DENF and CHIK, which is critical to identify regions that may have experienced the greatest burden of VBDs. The relative risk of CHIK and DENF for each Colombian municipality belonging to a univariate and multivariate cluster is reported to facilitate targeted interventions. Finally, we visualize the results in a three-dimensional environment to examine the size and duration of the clusters. Our approach is the first of its kind to examine multiple VBDs in Colombia simultaneously, while the 3D visualizations are a novel way of illustrating the dynamics of space-time clusters of disease.

A Novel Framework for Sentiment and Emoticon-Based Clustering and Indexing of Tweets

Social Networks have become an important part of people’s life as they share their day-to-day happenings, portray their opinions on various topics or find out information related to their queries. Due to the overwhelming volume of tweets generated on a daily basis, it is not possible to read all the tweets and differentiate the tweets based on the views or the attitude they portray only. The primary objective of sentiment analysis is to find out the attitude/emotion/opinion/sentiment that is present in the material provided. Commonly, the tweets can be clustered on the basis of them being positive or negative i.e. being in favour of the topic or being against the topic. The clustering and indexing of the tweets help in the organisation, searching, and summarisation of task. Twitter data are considered as Big Data and the information contained within the tweets is unstructured and if utilised properly can be very useful for educational and governance purposes. In this paper, a method is presented which clusters and then indexes the tweets on the basis of the sentiments and emoticons that are present in the tweet.

Observing vegetation phenology through social media

The widespread use of social media has created a valuable but underused source of data for the environmental sciences. We demonstrate the potential for images posted to the website Twitter to capture variability in vegetation phenology across United States National Parks. We process a subset of images posted to Twitter within eight U.S. National Parks, with the aim of understanding the amount of green vegetation in each image. Analysis of the relative greenness of the images show statistically significant seasonal cycles across most National Parks at the 95% confidence level, consistent with springtime green-up and fall senescence. Additionally, these social media-derived greenness indices correlate with monthly mean satellite NDVI (r = 0.62), reinforcing the potential value these data could provide in constraining models and observing regions with limited high quality scientific monitoring.

Using tweets to understand changes in the spatial crime distribution for hockey events in Vancouver

The use of social media data for the spatial analysis of crime patterns during social events has proven to be instructive. This study analyzes the geography of crime considering hockey game days, criminal behaviour, and Twitter activity. Specifically, we consider the relationship between geolocated crime-related Twitter activity and crime. We analyze six property crime types that are aggregated to the dissemination area base unit in Vancouver, for two hockey seasons through a game and non-game temporal resolution. Using the same method, geolocated Twitter messages and environmental variables are aggregated to dissemination areas. We employ spatial clustering, dictionary-based mining for tweets, spatial autocorrelation, and global and local regression models (spatial lag and geographically weighted regression). Findings show an important influence of Twitter data for theft-from-vehicle and mischief, mostly on hockey game days. Relationships from the geographically weighted regression models indicate that tweets are a valuable independent variable that can be used in explaining and understanding crime patterns.

Mention effect in information diffusion on a micro-blogging network

Micro-blogging systems have become one of the most important ways for information sharing. Network structure and users' interactions such as forwarding behaviors have aroused considerable research attention, while mention, as a key feature in micro-blogging platforms which can improve the visibility of a message and direct it to a particular user beyond the underlying social structure, is seldom studied in previous works. In this paper, we empirically study the mention effect in information diffusion, using the dataset from a population-scale social media website. We find that users with high number of followers would receive much more mentions than others. We further investigate the effect of mention in information diffusion by examining the response probability with respect to the number of mentions in a message and observe a saturation at around 5 mentions. Furthermore, we find that the response probability is the highest when a reciprocal followship exists between users, and one is more likely to receive a target user's response if they have similar social status. To illustrate these findings, we propose the response prediction task and formulate it as a binary classification problem. Extensive evaluation demonstrates the effectiveness of discovered factors. Our results have consequences for the understanding of human dynamics on the social network, and potential implications for viral marketing and public opinion monitoring.

Piecing together the puzzle: Improving event content coverage for real-time sub-event detection using adaptive microblog crawling

In an age when people are predisposed to report real-world events through their social media accounts, many researchers value the benefits of mining user generated content from social media. Compared with the traditional news media, social media services, such as Twitter, can provide more complete and timely information about the real-world events. However events are often like a puzzle and in order to solve the puzzle/understand the event, we must identify all the sub-events or pieces. Existing Twitter event monitoring systems for sub-event detection and summarization currently typically analyse events based on partial data as conventional data collection methodologies are unable to collect comprehensive event data. This results in existing systems often being unable to report sub-events in real-time and often in completely missing sub-events or pieces in the broader event puzzle. This paper proposes a Sub-event detection by real-TIme Microblog monitoring (STRIM) framework that leverages the temporal feature of an expanded set of news-worthy event content. In order to more comprehensively and accurately identify sub-events this framework first proposes the use of adaptive microblog crawling. Our adaptive microblog crawler is capable of increasing the coverage of events while minimizing the amount of non-relevant content. We then propose a stream division methodology that can be accomplished in real time so that the temporal features of the expanded event streams can be analysed by a burst detection algorithm. In the final steps of the framework, the content features are extracted from each divided stream and recombined to provide a final summarization of the sub-events. The proposed framework is evaluated against traditional event detection using event recall and event precision metrics. Results show that improving the quality and coverage of event contents contribute to better event detection by identifying additional valid sub-events. The novel combination of our proposed adaptive crawler and our stream division/recombination technique provides significant gains in event recall (44.44%) and event precision (9.57%). The addition of these sub-events or pieces, allows us to get closer to solving the event puzzle.

Uncovering and Predicting the Dynamic Process of Collective Attention with Survival Theory

The subject of collective attention is in the center of this era of information explosion. It is thus of great interest to understand the fundamental mechanism underlying attention in large populations within a complex evolving system. Moreover, an ability to predict the dynamic process of collective attention for individual items has important implications in an array of areas. In this report, we propose a generative probabilistic model using a self-excited Hawkes process with survival theory to model and predict the process through which individual items gain their attentions. This model explicitly captures three key ingredients: the intrinsic attractiveness of an item, characterizing its inherent competitiveness against other items; a reinforcement mechanism based on sum of each previous attention triggers; and a power-law temporal relaxation function, corresponding to the aging in the ability to attract new attentions. Experiments on two population-scale datasets demonstrate that this model consistently outperforms the state-of-the-art methods.

Virtual World Currency Value Fluctuation Prediction System Based on User Sentiment Analysis

In this paper, we present a method for predicting the value of virtual currencies used in virtual gaming environments that support multiple users, such as massively multiplayer online role-playing games (MMORPGs). Predicting virtual currency values in a virtual gaming environment has rarely been explored; it is difficult to apply real-world methods for predicting fluctuating currency values or shares to the virtual gaming world on account of differences in domains between the two worlds. To address this issue, we herein predict virtual currency value fluctuations by collecting user opinion data from a virtual community and analyzing user sentiments or emotions from the opinion data. The proposed method is straightforward and applicable to predicting virtual currencies as well as to gaming environments, including MMORPGs. We test the proposed method using large-scale MMORPGs and demonstrate that virtual currencies can be effectively and efficiently predicted with it.