Twitter as a sentinel in emergency situations: lessons from the Boston marathon explosions

Social Sensing and Individual Brands in Sports: Lessons Learned from English-Language Reactions on Twitter to Pau Gasol's Retirement Announcement

Pau Gasol announced his retirement on 5 October 2021. Subsequently, a number of users virtually reacted. Twitter is one of the most popular social media platforms, with more than 368 million active users, generating large-scale social data. This study used data from Twitter for analyzing social sensing related to an individual brand, Pau Gasol's retirement announcement, from a quantitative and qualitative content analysis perspective. Pau Gasol's farewell can be considered a unique event to which many people are emotionally attached, providing a great opportunity for understanding sports virtual ecosystems. A total of 2089 tweets in the English language were recovered from Tuesday 5 October 2021 at 3:00 to Thursday 7 October 2021 at 23:59, Greenwich Mean Time +00:00 time zone. During this time, posts were observed to be mainly influential during and right after Pau Gasol's ceremony. The tweets that created more impact were published by news sources or by sports reporters. Lastly, the themes that emerged showed that the Los Angeles Lakers and the NBA were the two most important milestones in Pau Gasol's career. The data can be used to detect potential areas of controversy or other issues to be addressed in order to preserve the athlete's public image. These results are considered of interest for reaching better knowledge of sport virtual environments through social sensing, supporting the idea of users acting as sensors.

Social Bots Detection via Fusing BERT and Graph Convolutional Networks

The online social media ecosystem is becoming more and more confused because of more and more fake information and the social media of malicious users’ fake content; at the same time, unspeakable pain has been brought to mankind. Social robot detection uses supervised classification based on artificial feature extraction. However, user privacy is also involved in using these methods, and the hidden feature information is also ignored, such as semi-supervised algorithms with low utilization rates and graph features. In this work, we symmetrically combine BERT and GCN (Graph Convolutional Network, GCN) and propose a novel model that combines large scale pretraining and transductive learning for social robot detection, BGSRD. BGSRD constructs a heterogeneous graph over the dataset and represents Twitter as nodes using BERT representations. Corpus learning via text graph convolution network is a single text graph, which is mainly built for corpus-based on word co-occurrence and document word relationship. BERT and GCN modules can be jointly trained in BGSRD to achieve the best of merit, training data and unlabeled test data can spread label influence through graph convolution and can be carried out in the large-scale pre-training of massive raw data and the transduction learning of joint learning representation. The experiment shows that a better performance can also be achieved by BGSRD on a wide range of social robot detection datasets.

Topic-Emotion Propagation Mechanism of Public Emergencies in Social Networks

The information propagation of emergencies in social networks is often accompanied by the dissemination of the topic and emotion. As a virtual sensor of public emergencies, social networks have been widely used in data mining, knowledge discovery, and machine learning. From the perspective of network, this study aims to explore the topic and emotion propagation mechanism, as well as the interaction and communication relations of the public in social networks under four types of emergencies, including public health events, accidents and disasters, social security events, and natural disasters. Event topics were identified by Word2vec and K-means clustering. The biLSTM model was used to identify emotion in posts. The propagation maps of topic and emotion were presented visually on the network, and the synergistic relationship between topic and emotion propagation as well as the communication characteristics of multiple subjects were analyzed. The results show that there were similarities and differences in the propagation mechanism of topic and emotion in different types of emergencies. There was a positive correlation between topic and emotion of different types of users in social networks in emergencies. Users with a high level of topic influence were often accompanied by a high level of emotion appeal.

Exploring discussions of health and risk and public sentiment in Massachusetts during COVID-19 pandemic mandate implementation: A Twitter analysis

As policies are adjusted throughout the COVID-19 pandemic according to public health best practices, there is a need to balance the importance of social distancing in preventing viral spread with the strain that these governmental public safety mandates put on public mental health. Thus, there is need for continuous observation of public sentiment and deliberation to inform further adaptation of mandated interventions. In this study, we explore how public response may be reflected in Massachusetts (MA) via social media by specifically exploring temporal patterns in Twitter posts (tweets) regarding sentiment and discussion of topics. We employ interrupted time series centered on (1) Massachusetts State of Emergency declaration (March 10), (2) US State of Emergency declaration (March 13) and (3) Massachusetts public school closure (March 17) to explore changes in tweet sentiment polarity (net negative/positive), expressed anxiety and discussion on risk and health topics on a random subset of all tweets coded within Massachusetts and published from January 1 to May 15, 2020 (n = 2.8 million). We find significant differences between tweets published before and after mandate enforcement for Massachusetts State of Emergency (increased discussion of risk and health, decreased polarity and increased anxiety expression), US State of Emergency (increased discussion of risk and health, and increased anxiety expression) and Massachusetts public school closure (increased discussion of risk and decreased polarity). Our work further validates that Twitter data is a reasonable way to monitor public sentiment and discourse within a crisis, especially in conjunction with other observation data.

•

Twitter can be used to track the emotions of the public during times of crises.

•

During COVID-19 shelter-in-place an increase in discussions about risk and health, and anxiety levels was seen on Twitter.

•

Real-time information from Twitter may be used to make quick evidence-based decisions based on public reactions.

Use of Social Media by Hospitals and Clinics in Japan: Descriptive Study

BACKGROUND

The use of social media by hospitals has become widespread in the United States and Western European countries. However, in Japan, the extent to which hospitals and clinics use social media is unknown. Furthermore, recent revisions to the Medical Care Act may subject social media content to regulation.

OBJECTIVE

The purpose of this study was to examine social media use in Japanese hospitals and clinics. We investigated the adoption of social media, analyzed social media content, and compared content with medical advertising guidelines.

METHODS

We randomly sampled 300 hospitals and 300 clinics from a list of medical institutions that was compiled by the Ministry of Health, Labour and Welfare. We performed web and social media (Facebook and Twitter) searches using the hospital and clinic names to determine whether they had social media accounts. We collected Facebook posts and Twitter tweets and categorized them based on their content (eg, health promotion, participation in academic meetings and publications, public relations or news announcements, and recruitment). We compared the collected content with medical advertising guidelines.

RESULTS

We found that 26.0% (78/300) of the hospitals and 7.7% (23/300) of the clinics used Facebook, Twitter, or both. Public relations or news announcements accounted for 53.99% (724/1341) of the Facebook posts by hospitals and 58.4% (122/209) of the Facebook posts by clinics. In hospitals, 16/1341 (1.19%) Facebook posts and 6/574 (1.0%) tweets and in clinics, 8/209 (3.8%) Facebook posts and 15/330 (4.5%) tweets could conflict medical advertising guidelines.

CONCLUSIONS

Fewer hospitals and clinics in Japan use social media as compared to other countries. Social media were mainly used for public relations. Some content disseminated by medical institutions could conflict with medical advertising guidelines. This study may serve as a reference for medical institutions to guide social media usage and may help improve medical website advertising in Japan.

Evaluating Geo-Tagged Twitter Data to Analyze Tourist Flows in Styria, Austria

The research focuses on detecting tourist flows in the Province of Styria in Austria based on crowdsourced data. Twitter data were collected in the time range from 2008 until August 2018. Extracted tweets were submitted to an extensive filtering process within non-relational database MongoDB. Hotspot Analysis and Kernel Density Estimation methods were applied, to investigate spatial distribution of tourism relevant tweets under temporal variations. Furthermore, employing the VADER method an integrated semantic analysis provides sentiments of extracted tweets. Spatial analyses showed that detected Hotspots correspond to typical Styrian touristic areas. Apart from mainly successful sentiment analysis, it pointed out also a problematic aspect of working with multilingual data. For evaluation purposes, the official tourism data from the Province of Styria and federal Statistical Office of Austria played a role of ground truth data. An evaluation with Pearson’s correlation coefficient was employed, which proves a statistically significant correlation between Twitter data and reference data. In particular, the paper shows that crowdsourced data on a regional level can serve as accurate indicator for the behaviour and movement of users.

Information technology in emergency management of COVID-19 outbreak

Emergency management of the emerging infectious disease outbreak is critical for public health threats. Currently, control of the COVID-19 outbreak is an international concern and has become a crucial challenge in many countries. This article reviews significant information technologyIT) applications in emergency management of COVID-19 by considering the prevention/mitigation, preparedness, response, and recovery phases of the crisis. This review was conducted using MEDLINE PubMed), Embase, IEEE, and Google Scholar. Expert opinions were collected to show existence gaps, useful technologies for each phase of emergency management, and future direction. Results indicated that various IT-based systems such as surveillance systems, artificial intelligence, computational methods, Internet of things, remote sensing sensor, online service, and GIS geographic information system) could have different outbreak management applications, especially in response phases. Information technology was applied in several aspects, such as increasing the accuracy of diagnosis, early detection, ensuring healthcare providers' safety, decreasing workload, saving time and cost, and drug discovery. We categorized these applications into four core topics, including diagnosis and prediction, treatment, protection, and management goals, which were confirmed by five experts. Without applying IT, the control and management of the crisis could be difficult on a large scale. For reducing and improving the hazard effect of disaster situations, the role of IT is inevitable. In addition to the response phase, communities should be considered to use IT capabilities in prevention, preparedness, and recovery phases. It is expected that IT will have an influential role in the recovery phase of COVID-19. Providing IT infrastructure and financial support by the governments should be more considered in facilitating IT capabilities.

Public Opinion About E-Cigarettes on Chinese Social Media: A Combined Study of Text Mining Analysis and Correspondence Analysis

Background

Electronic cigarettes (e-cigarettes) have become increasingly popular. China has accelerated its legislation on e-cigarettes in recent years by issuing two policies to regulate their use: the first on August 26, 2018, and the second on November 1, 2019. Social media provide an efficient platform to access information on the public opinion of e-cigarettes.

Objective

To gain insight into how policies have influenced the reaction of the Chinese public to e-cigarettes, this study aims to understand what the Chinese public say about e-cigarettes and how the focus of discussion might have changed in the context of policy implementation.

Methods

This study uses a combination of text mining and correspondence analysis to content analyze 1160 e-cigarette–related questions and their corresponding answers from Zhihu, China’s largest question-and-answer platform and one of the country’s most trustworthy social media sources. From January 1, 2017, to December 31, 2019, Python was used to text mine the most frequently used words and phrases in public e-cigarette discussions on Zhihu. The correspondence analysis was used to examine the similarities and differences between high-frequency words and phrases across 3 periods (ie, January 1, 2017, to August 27, 2018; August 28, 2018, to October 31, 2019; and November 1, 2019, to January 1, 2020).

Results

The results of the study showed that the consistent themes across time were comparisons with traditional cigarettes, health concerns, and how to choose e-cigarette products. The issuance of government policies on e-cigarettes led to a change in the focus of public discussion. The discussion of e-cigarettes in period 1 mainly focused on the use and experience of e-cigarettes. In period 2, the public’s attention was not only on the substances related to e-cigarettes but also on the smoking cessation functions of e-cigarettes. In period 3, the public shifted their attention to the e-cigarette industry and government policy on the banning of e-cigarette sales to minors.

Conclusions

Social media are an informative source, which can help policy makers and public health professionals understand the public’s concerns over and understanding of e-cigarettes. When there was little regulation, public discussion was greatly influenced by industry claims about e-cigarettes; however, once e-cigarette policies were issued, these policies, to a large extent, set the agenda for public discussion. In addition, media reporting of these policies might have greatly influenced the way e-cigarette policies were discussed. Therefore, monitoring e-cigarette discussions on social media and responding to them in a timely manner will both help improve the public’s e-cigarette literacy and facilitate the implementation of e-cigarette–related policies.

Using Twitter for crisis communications in a natural disaster: Hurricane Harvey

This article examines the use of social media, specifically Twitter, in crisis communications during a natural disaster and how it can provide information, guidance, reassurance and hope to victims while keeping others across the nation and the world apprised of the situation so they can provide assistance, as needed. A case study looks at how the mayor of Houston, Texas, Sylvester Turner, used Twitter during Hurricane Harvey in August and September of 2017. The case study is analyzed using restorative rhetoric theory, revealing the use of Twitter by Mayor Turner to be a strong example of successful restorative rhetoric during a natural disaster. This research affirms the findings of other researchers that the restorative rhetoric stages overlap, and that the theory may be improved with some variation based on crisis type. This research also shows that Mayor Turner's use of Twitter exemplifies best practices for using social media in crisis communications with very few opportunities for improvement. This article offers suggestions to crisis managers on how to use Twitter to prepare for, communicate during, and go forward following a natural disaster.

A computational study of mental health awareness campaigns on social media

As public discourse continues to progress online, it is important for mental health advocates, public health officials, and other curious parties and stakeholders, ranging from researchers, to those affected by the issue, to be aware of the advancing new mediums in which the public can share content ranging from useful resources and self-help tips to personal struggles with respect to both illness and its stigmatization. A better understanding of this new public discourse on mental health, often framed as social media campaigns, can help perpetuate the allocation of sparse mental health resources, the need for educational awareness, and the usefulness of community, with an opportunity to reach those seeking help at the right moment. The objective of this study was to understand the nature of and engagement around mental health content shared on mental health campaigns, specifically #MyTipsForMentalHealth on Twitter around World Mental Health Awareness Day in 2017. We collected 14,217 Twitter posts from 10,805 unique users between September and October 2017 that contained the hashtag #MyTipsForMentalHealth. With the involvement of domain experts, we hand-labeled 700 posts and categorized them as (a) Fact, (b) Stigmatizing, (c) Inspirational, (d) Medical/Clinical Tip, (e) Resource Related, (f) Lifestyle or Social Tip or Personal View, and (g) Off Topic. After creating a "seed" machine learning classifier, we used both unsupervised and semi supervised methods to classify posts into the various expert identified topical categories. We also performed a content analysis to understand how information on different topics spread through social networks. Our support vector machine classification algorithm achieved a mean cross-validation accuracy of 0.81 and accuracy of 0.64 on unseen data. We found that inspirational Twitter posts were the most spread with a mean of 4.17 retweets, and stigmatizing content was second with a mean of 3.66 retweets. Classification of social media-related mental health interactions offers valuable insights on public sentiment as well as a window into the evolving world of online self-help and the varied resources within. Our results suggest an important role for social media-based peer support to not only guide information seekers to useful content and local resources but also illuminate the socially-insular aspects of stigmatization. However, our results also reflect the challenges of quantifying the heterogeneity of mental health content on social media and the need for novel machine learning methods customized to the challenges of the field.

Sudden Infant Death Syndrome and Safe Sleep on Twitter: Analysis of Influences and Themes to Guide Health Promotion Efforts

BACKGROUND

In the United States, sudden infant death syndrome (SIDS) is the leading cause of death in infants aged 1 month to 1 year. Approximately 3500 infants die from SIDS and sleep-related reasons on a yearly basis. Unintentional sleep-related deaths and bed sharing, a known risk factor for SIDS, are on the rise. Furthermore, ethnic disparities exist among those most affected by SIDS. Despite public health campaigns, infant mortality persists. Given the popularity of social media, understanding social media conversations around SIDS and safe sleep may assist the medical and public health communities with information needed to spread, reinforce, or counteract false information regarding SIDS and safe sleep.

OBJECTIVE

The objective of our study was to investigate the social media conversation around SIDS and safe sleep to understand the possible influences and guide health promotion efforts and public health research as well as enable health professionals to engage in directed communication regarding this topic.

METHODS

We used textual analytics to identify topics and extract meanings contained in unstructured textual data. Twitter messages were captured during September, October, and November in 2017. Tweets and retweets were collected using NUVI software in conjunction with Twitter's search API using the keywords: "sids," "infant death syndrome," "sudden infant death syndrome," and "safe sleep." This returned a total of 41,358 messages, which were analyzed using text mining and social media monitoring software.

RESULTS

Multiple themes were identified, including recommendations for safe sleep to prevent SIDS, safe sleep devices, the potential causes of SIDS, and how breastfeeding reduces SIDS. Compared with September and November, more personal and specific stories of infant loss were demonstrated in October (Pregnancy and Infant Loss Awareness Month). The top influencers were news organizations, universities, and health-related organizations.

CONCLUSIONS

We identified valuable topics discussed and shared on Twitter regarding SIDS and safe sleep. The study results highlight the contradicting information a subset of the population is exposed to regarding SIDS and the continued controversy over vaccines. In addition, this analysis emphasizes the lack of public health organizations' presence on Twitter compared with the influence of universities and news media organizations. The results also demonstrate the prevalence of safe sleep products that are embedded in safe sleep messaging. These findings can assist providers in speaking about relevant topics when engaging in conversations about the prevention of SIDS and the promotion of safe sleep. Furthermore, public health agencies and advocates should utilize social media and Twitter to better communicate accurate health information as well as continue to combat the spread of false information.

Comparing Twitter data to routine data sources in public health surveillance for the 2015 Pan/Parapan American Games: an ecological study

Objectives

This study examined Twitter for public health surveillance during a mass gathering in Canada with two objectives: to explore the feasibility of acquiring, categorizing and using geolocated Twitter data and to compare Twitter data against other data sources used for Pan Parapan American Games (P/PAG) surveillance.

Methods

Syndrome definitions were created using keyword categorization to extract posts from Twitter. Categories were developed iteratively for four relevant syndromes: respiratory, gastrointestinal, heat-related illness, and influenza-like illness (ILI). All data sources corresponded to the location of Toronto, Canada. Twitter data were acquired from a publicly available stream representing a 1% random sample of tweets from June 26 to September 10, 2015. Cross-correlation analyses of time series data were conducted between Twitter and comparator surveillance data sources: emergency department visits, telephone helpline calls, laboratory testing positivity rate, reportable disease data, and temperature.

Results

The frequency of daily tweets that were classified into syndromes was low, with the highest mean number of daily tweets being for ILI and respiratory syndromes (22.0 and 21.6, respectively) and the lowest, for the heat syndrome (4.1). Cross-correlation analyses of Twitter data demonstrated significant correlations for heat syndrome with two data sources: telephone helpline calls (r = 0.4) and temperature data (r = 0.5).

Conclusion

Using simple syndromes based on keyword classification of geolocated tweets, we found a correlation between tweets and two routine data sources for heat alerts, the only public health event detected during P/PAG. Further research is needed to understand the role for Twitter in surveillance.

Electronic supplementary material

The online version of this article (10.17269/s41997-018-0059-0) contains supplementary material, which is available to authorized users.

The performance of the IES-R for Latinos and non-Latinos: Assessing measurement invariance

Violent acts on university campuses are becoming more frequent. Enrollment rates of Latinos at universities is increasing. Research has indicated that youths are more susceptible to trauma, particularly Latinos. Thus, it is imperative to evaluate the validity of commonly used posttraumatic stress measures among Latino college students. The Impact of Event Scale-Revised (IES-R) is one of the most commonly used metrics of posttraumatic stress disorder symptomatology. However, it is largely unknown if the IES-R is measuring the same construct across different sub-samples (e.g. Latino versus non-Latino). The current study aimed to assess measurement invariance for the IES-R between Latino and non-Latino participants. A total of 545 participants completed the IES-R. One- and three-factor scoring solutions were compared using confirmatory factor analyses. Measurement invariance was then evaluated by estimating several multiple-group confirmatory factor analytic models. Four models with an increasing degree of invariance across groups were compared. A significant χ2 difference test was used to indicate a significant change in model fit between nested models within the measurement invariance testing process. The three-factor scoring solution could not be used for the measurement invariance process because the subscale correlations were too high for estimation (rs 0.92-1.00). Therefore, the one-factor model was used for the invariance testing process. Invariance was met for each level of invariance: configural, metric, scalar, and strict. All measurement invariance testing results indicated that the one-factor solution for the IES-R was equivalent for the Latino and non-Latino participants.

Monitoring the environment and human sentiment on the Great Barrier Reef: Assessing the potential of collective sensing

With the growth of smartphone usage the number of social media posts has significantly increased and represents potentially valuable information for management, including of natural resources and the environment. Already, evidence of using 'human sensor' in crises management suggests that collective knowledge could be used to complement traditional monitoring. This research uses Twitter data posted from the Great Barrier Reef region, Australia, to assess whether the extent and type of data could be used to Great Barrier Reef organisations as part of their monitoring program. The analysis reveals that large amounts of tweets, covering the geographic area of interest, are available and that the pool of information providers is greatly enhanced by the large number of tourists to this region. A keyword and sentiment analysis demonstrates the usefulness of the Twitter data, but also highlights that the actual number of Reef-related tweets is comparatively small and lacks specificity. Suggestions for further steps towards the development of an integrative data platform that incorporates social media are provided.

Using Twitter for Demographic and Social Science Research: Tools for Data Collection and Processing

Despite recent and growing interest in using Twitter to examine human behavior and attitudes, there is still significant room for growth regarding the ability to leverage Twitter data for social science research. In particular, gleaning demographic information about Twitter users-a key component of much social science research-remains a challenge. This article develops an accurate and reliable data processing approach for social science researchers interested in using Twitter data to examine behaviors and attitudes, as well as the demographic characteristics of the populations expressing or engaging in them. Using information gathered from Twitter users who state an intention to not vote in the 2012 presidential election, we describe and evaluate a method for processing data to retrieve demographic information reported by users that is not encoded as text (e.g., details of images) and evaluate the reliability of these techniques. We end by assessing the challenges of this data collection strategy and discussing how large-scale social media data may benefit demographic researchers.

ORBiT: Oak Ridge biosurveillance toolkit for public health dynamics

Background

The digitization of health-related information through electronic health records (EHR) and electronic healthcare reimbursement claims and the continued growth of self-reported health information through social media provides both tremendous opportunities and challenges in developing effective biosurveillance tools. With novel emerging infectious diseases being reported across different parts of the world, there is a need to build systems that can track, monitor and report such events in a timely manner. Further, it is also important to identify susceptible geographic regions and populations where emerging diseases may have a significant impact.

Methods

In this paper, we present an overview of Oak Ridge Biosurveillance Toolkit (ORBiT), which we have developed specifically to address data analytic challenges in the realm of public health surveillance. In particular, ORBiT provides an extensible environment to pull together diverse, large-scale datasets and analyze them to identify spatial and temporal patterns for various biosurveillance-related tasks.

Results

We demonstrate the utility of ORBiT in automatically extracting a small number of spatial and temporal patterns during the 2009-2010 pandemic H1N1 flu season using claims data. These patterns provide quantitative insights into the dynamics of how the pandemic flu spread across different parts of the country. We discovered that the claims data exhibits multi-scale patterns from which we could identify a small number of states in the United States (US) that act as "bridge regions" contributing to one or more specific influenza spread patterns. Similar to previous studies, the patterns show that the south-eastern regions of the US were widely affected by the H1N1 flu pandemic. Several of these south-eastern states act as bridge regions, which connect the north-east and central US in terms of flu occurrences.

Conclusions

These quantitative insights show how the claims data combined with novel analytical techniques can provide important information to decision makers when an epidemic spreads throughout the country. Taken together ORBiT provides a scalable and extensible platform for public health surveillance.

Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit

We describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flu incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.

Sources of spatial animal and human health data: Casting the net wide to deal more effectively with increasingly complex disease problems

During the last 30years it has become commonplace for epidemiological studies to collect locational attributes of disease data. Although this advancement was driven largely by the introduction of handheld global positioning systems (GPS), and more recently, smartphones and tablets with built-in GPS, the collection of georeferenced disease data has moved beyond the use of handheld GPS devices and there now exist numerous sources of crowdsourced georeferenced disease data such as that available from georeferencing of Google search queries or Twitter messages. In addition, cartography has moved beyond the realm of professionals to crowdsourced mapping projects that play a crucial role in disease control and surveillance of outbreaks such as the 2014 West Africa Ebola epidemic. This paper provides a comprehensive review of a range of innovative sources of spatial animal and human health data including data warehouses, mHealth, Google Earth, volunteered geographic information and mining of internet-based big data sources such as Google and Twitter. We discuss the advantages, limitations and applications of each, and highlight studies where they have been used effectively.

Network structure and community evolution on Twitter: human behavior change in response to the 2011 Japanese earthquake and tsunami

To investigate the dynamics of social networks and the formation and evolution of online communities in response to extreme events, we collected three datasets from Twitter shortly before and after the 2011 earthquake and tsunami in Japan. We find that while almost all users increased their online activity after the earthquake, Japanese speakers, who are assumed to be more directly affected by the event, expanded the network of people they interact with to a much higher degree than English speakers or the global average. By investigating the evolution of communities, we find that the behavior of joining or quitting a community is far from random: users tend to stay in their current status and are less likely to join new communities from solitary or shift to other communities from their current community. While non-Japanese speakers did not change their conversation topics significantly after the earthquake, nearly all Japanese users changed their conversations to earthquake-related content. This study builds a systematic framework for investigating human behaviors under extreme events with online social network data and our findings on the dynamics of networks and communities may provide useful insight for understanding how patterns of social interaction are influenced by extreme events.

Twitter in the cross fire--the use of social media in the Westgate Mall terror attack in Kenya

On September 2013 an attack on the Westgate mall in Kenya led to a four day siege, resulting in 67 fatalities and 175 wounded. During the crisis, Twitter became a crucial channel of communication between the government, emergency responders and the public, facilitating the emergency management of the event. The objectives of this paper are to present the main activities, use patterns and lessons learned from the use of the social media in the crisis. Using TwitterMate, a system developed to collect, store and analyze tweets, the main hashtags generated by the crowd and specific Twitter accounts of individuals, emergency responders and NGOs, were followed throughout the four day siege. A total of 67,849 tweets were collected and analyzed. Four main categories of hashtags were identified: geographical locations, terror attack, social support and organizations. The abundance of Twitter accounts providing official information made it difficult to synchronize and follow the flow of information. Many organizations posted simultaneously, by their manager and by the organization itself. Creating situational awareness was facilitated by information tweeted by the public. Threat assessment was updated through the information posted on social media. Security breaches led to the relay of sensitive data. At times, misinformation was only corrected after two days. Social media offer an accessible, widely available means for a bi-directional flow of information between the public and the authorities. In the crisis, all emergency responders used and leveraged social media networks for communicating both with the public and among themselves. A standard operating procedure should be developed to enable multiple responders to monitor, synchronize and integrate their social media feeds during emergencies. This will lead to better utilization and optimization of social media resources during crises, providing clear guidelines for communications and a hierarchy for dispersing information to the public and among responding organizations.

Big Data in Science and Healthcare: A Review of Recent Literature and Perspectives. Contribution of the IMIA Social Media Working Group

OBJECTIVES

As technology continues to evolve and rise in various industries, such as healthcare, science, education, and gaming, a sophisticated concept known as Big Data is surfacing. The concept of analytics aims to understand data. We set out to portray and discuss perspectives of the evolving use of Big Data in science and healthcare and, to examine some of the opportunities and challenges.

METHODS

A literature review was conducted to highlight the implications associated with the use of Big Data in scientific research and healthcare innovations, both on a large and small scale.

RESULTS

Scientists and health-care providers may learn from one another when it comes to understanding the value of Big Data and analytics. Small data, derived by patients and consumers, also requires analytics to become actionable. Connectivism provides a framework for the use of Big Data and analytics in the areas of science and healthcare. This theory assists individuals to recognize and synthesize how human connections are driving the increase in data. Despite the volume and velocity of Big Data, it is truly about technology connecting humans and assisting them to construct knowledge in new ways. Concluding Thoughts: The concept of Big Data and associated analytics are to be taken seriously when approaching the use of vast volumes of both structured and unstructured data in science and health-care. Future exploration of issues surrounding data privacy, confidentiality, and education are needed. A greater focus on data from social media, the quantified self-movement, and the application of analytics to "small data" would also be useful.

Analysis of twitter users' sharing of official new york storm response messages

Background

Twitter is a social network where users read, send, and share snippets of text (“tweets”). Tweets can be disseminated through multiple means; on desktop computers, laptops, and mobile devices, over ethernet, Wi-Fi or cellular networks. This redundancy positions Twitter as a useful tool for disseminating information to the public during emergencies or disasters. Previous research on dissemination of information using Twitter has mostly investigated the characteristics of tweets that are most effective in raising consumer awareness about a new product or event. In particular, they describe characteristics that increase the chance the messages will be shared ("retweeted") by users. In comparison, little has been published on how information from municipal or state government agencies spreads on Twitter during emergency situations. Retweeting these messages is a way to enhance public awareness of potentially important instructions from public officials in a disaster.

Objective

The aim of this study is to (1) describe the tweets of select New York State and New York City agencies by public officials surrounding two notable recent winter storms that required a large-scale emergency response, and (2) identify the characteristics of the tweets of public officials that were most disseminated (retweeted).

Methods

For one week surrounding Superstorm Sandy (October 2012) and the winter blizzard Nemo (February 2013), we collected (1) tweets from the official accounts for six New York governmental agencies, and (2) all tweets containing the hashtags #sandy (or #nemo) and #nyc. From these data we calculated how many times a tweet was retweeted, controlling for differences in baseline activity in each account. We observed how many hashtags and links each tweet contained. We also calculated the lexical diversity of each tweet, a measure of the range of vocabulary used.

Results

During the Sandy storm, 3242 shared (retweeted) messages from public officials were collected. The lexical diversity of official tweets was similar (2.25-2.49) and well below the average for non-official tweets mentioning #sandy and #nyc (3.82). Most official tweets were with substantial retweets including a link for further reading. Of the 448 tweets analyzed from six official city and state Twitter accounts from the Nemo blizzard, 271 were related to the storm, and 174 had actionable information for the public. Actionable storm messages were retweeted approximately 24x per message, compared to 31x per message for general storm information.

Conclusions

During two weather emergencies, New York public officials were able to convey storm-related information that was shared widely beyond existing follower bases, potentially improving situational awareness and disaster response. Official Sandy tweets, characterized by a lower lexical diversity score than other city- and Sandy-related tweets, were likely easier to understand, and often linked to further information and resources. Actionable information in the Nemo blizzard, such as specific instructions and cancellation notices, was not shared as often as more general warnings and “fun facts,” suggesting agencies mix important instructions with more general news and trivia, as a way of reaching the broadest audience during a disaster.

Translational informatics in personalized medicine: an update for 2014

Many things have changed but much has remained the same as we have seen a dramatic increase in the generation of genetics, genomics and a variety of clinical data leading to increased data density and continued challenges in organizing and managing that data in pursuit of personalized medicine. Simultaneously, we have seen an increase in commercial and open-source solutions, and marked movement toward open sharing of tools and data in public–private partnerships, yet still few examples of traditional companion diagnostics for personalized medicine products. Most encouraging are examples of focused public and private efforts that have resulted in knowledge leading to critical assessment of existing therapies and the development of new therapies. These examples lay highly emulatable informatics foundations for rapid advances in personalized medicine.

Innovative uses of electronic health records and social media for public health surveillance

Electronic health records (EHRs) and social media have the potential to enrich public health surveillance of diabetes. Clinical and patient-facing data sources for diabetes surveillance are needed given its profound public health impact, opportunity for primary and secondary prevention, persistent disparities, and requirement for self-management. Initiatives to employ data from EHRs and social media for diabetes surveillance are in their infancy. With their transformative potential come practical limitations and ethical considerations. We explore applications of EHR and social media for diabetes surveillance, limitations to approaches, and steps for moving forward in this partnership between patients, health systems, and public health.

LESSONS LEARNED ABOUT PUBLIC HEALTH FROM ONLINE CROWD SURVEILLANCE

The Internet has forever changed the way people access information and make decisions about their healthcare needs. Patients now share information about their health at unprecedented rates on social networking sites such as Twitter and Facebook and on medical discussion boards. In addition to explicitly shared information about health conditions through posts, patients reveal data on their inner fears and desires about health when searching for health-related keywords on search engines. Data are also generated by the use of mobile phone applications that track users' health behaviors (e.g., eating and exercise habits) as well as give medical advice. The data generated through these applications are mined and repackaged by surveillance systems developed by academics, companies, and governments alike to provide insight to patients and healthcare providers for medical decisions. Until recently, most Internet research in public health has been surveillance focused or monitoring health behaviors. Only recently have researchers used and interacted with the crowd to ask questions and collect health-related data. In the future, we expect to move from this surveillance focus to the "ideal" of Internet-based patient-level interventions where healthcare providers help patients change their health behaviors. In this article, we highlight the results of our prior research on crowd surveillance and make suggestions for the future.