Discovering Health Topics in Social Media Using Topic Models

By aggregating self-reported health statuses across millions of users, we seek to characterize the variety of health information discussed in Twitter. We describe a topic modeling framework for discovering health topics in Twitter, a social media website. This is an exploratory approach with the goal of understanding what health topics are commonly discussed in social media. This paper describes in detail a statistical topic model created for this purpose, the Ailment Topic Aspect Model (ATAM), as well as our system for filtering general Twitter data based on health keywords and supervised classification. We show how ATAM and other topic models can automatically infer health topics in 144 million Twitter messages from 2011 to 2013. ATAM discovered 13 coherent clusters of Twitter messages, some of which correlate with seasonal influenza (r = 0.689) and allergies (r = 0.810) temporal surveillance data, as well as exercise (r = .534) and obesity (r = −.631) related geographic survey data in the United States. These results demonstrate that it is possible to automatically discover topics that attain statistically significant correlations with ground truth data, despite using minimal human supervision and no historical data to train the model, in contrast to prior work. Additionally, these results demonstrate that a single general-purpose model can identify many different health topics in social media.     

Social Media and Internet Driven Study Recruitment: Evaluating a New Model for Promoting Collaborator Engagement and Participation

Aims

A substantial challenge facing multicentre audit and research projects is timely recruitment of collaborators and their study centres. Cost-effective strategies are required and fee-free social media has previously been identified as a potential conduit. We investigated and evaluated the effectiveness of a novel multi-format social media and Internet strategy for targeted recruitment to a national multicentre cohort study.

Methods

Interventions involved a new Twitter account, including weekly live question-and-answer sessions, a new Facebook group page, online YouTube presentations and an information page on a national association website. Link tracking analysis was undertaken using Google Analytics, which was then related to subsequent registration. Social influence was calculated using the proprietary Klout score.

Results

Internet traffic analysis identified a total of 1562 unique registration site views, of which 285 originated from social media (18.2%). Some 528 unique registrations were received, with 96 via social media platforms (18.2%). Traffic source analysis identified a separate national association webpage as resulting in the majority of registration page views (15.8%), followed by Facebook (11.9%), Twitter (4.8%) and YouTube (1.5%). A combination of publicity through Facebook, Twitter and the dedicated national association webpage contributed to the greatest rise in registration traffic and accounted for 312 (48%) of the total registrations within a 2-week period. A Twitter ‘social influence’ (Klout) score of 42/100 was obtained during this period.

Conclusions

Targeted social media substantially aided study dissemination and collaborator recruitment. It acted as an adjunct to traditional methods, accounting for 18.2% of collaborator registration in a short time period with no associated financial costs. We provide a practical model for designing future recruitment campaigns, and recommend Facebook, Twitter and targeted websites as the most effective adjuncts for maximising cost-effective study recruitment.     

Discovering Social Events through Online Attention

Twitter is a major social media platform in which users send and read messages (“tweets”) of up to 140 characters. In recent years this communication medium has been used by those affected by crises to organize demonstrations or find relief. Because traffic on this media platform is extremely heavy, with hundreds of millions of tweets sent every day, it is difficult to differentiate between times of turmoil and times of typical discussion. In this work we present a new approach to addressing this problem. We first assess several possible “thermostats” of activity on social media for their effectiveness in finding important time periods. We compare methods commonly found in the literature with a method from economics. By combining methods from computational social science with methods from economics, we introduce an approach that can effectively locate crisis events in the mountains of data generated on Twitter. We demonstrate the strength of this method by using it to locate the social events relating to the Occupy Wall Street movement protests at the end of 2011.     

Social media user’s knowledge on soil plant relationship in Saudi Arabia

The study aimed to investigate the soil-plant relationship by looking at knowledge levels of social media users. The study examined the relationship between the users’ characteristics and their knowledge on soil-plant relationship. Online survey was designed and distributed to gather the data. The number of response was received from 383 respondents where 375 participants provided completed information and the remaining eight responses were eliminated due to quality standards. The results show most of the participants (68.8%) are moderately depend on social media to acquire knowledge on soil-plant relationship and indicated “Twitter” as the highly utilized platform followed by the “Youtube”. Meanwhile, 48.8% of the participants indicated that social media have a high impact on their knowledge-based information on soil-plant relationship and agricultural contents. Inferential analysis shows there was a significant positive relationship (p < 0.01) between independent variables; Twitter, Youtube, Instagram, and Snapchat and the degree of trust on these platforms, and the level’s knowledge on soil-plant relationship (dependent variable). Only 13% of the variance accounted for the impact of social media on participants’ agricultural knowledge-base can be predicted from the combination of participants’ reliance on a set of social media platforms (Twitter, Instagram, Youtube, and Snapchat). The study revealed the trust and confidence of the users using social media on agricultural information/soil plant relationship had a medium effect in social and educational research.     

Social media user’s knowledge on soil plant relationship in Saudi Arabia

The study aimed to investigate the soil-plant relationship by looking at knowledge levels of social media users. The study examined the relationship between the users’ characteristics and their knowledge on soil-plant relationship. Online survey was designed and distributed to gather the data. The number of response was received from 383 respondents where 375 participants provided completed information and the remaining eight responses were eliminated due to quality standards. The results show most of the participants (68.8%) are moderately depend on social media to acquire knowledge on soil-plant relationship and indicated “Twitter” as the highly utilized platform followed by the “Youtube”. Meanwhile, 48.8% of the participants indicated that social media have a high impact on their knowledge-based information on soil-plant relationship and agricultural contents. Inferential analysis shows there was a significant positive relationship (p < 0.01) between independent variables; Twitter, Youtube, Instagram, and Snapchat and the degree of trust on these platforms, and the level’s knowledge on soil-plant relationship (dependent variable). Only 13% of the variance accounted for the impact of social media on participants’ agricultural knowledge-base can be predicted from the combination of participants’ reliance on a set of social media platforms (Twitter, Instagram, Youtube, and Snapchat). The study revealed the trust and confidence of the users using social media on agricultural information/soil plant relationship had a medium effect in social and educational research.     

Diffusion of Messages from an Electronic Cigarette Brand to Potential Users through Twitter

Objective

This study explores the presence and actions of an electronic cigarette (e-cigarette) brand, Blu, on Twitter to observe how marketing messages are sent and diffused through the retweet (i.e., message forwarding) functionality. Retweet networks enable messages to reach additional Twitter users beyond the sender’s local network. We follow messages from their origin through multiple retweets to identify which messages have more reach, and the different users who are exposed.

Methods

We collected three months of publicly available data from Twitter. A combination of techniques in social network analysis and content analysis were applied to determine the various networks of users who are exposed to e-cigarette messages and how the retweet network can affect which messages spread.

Results

The Blu retweet network expanded during the study period. Analysis of user profiles combined with network cluster analysis showed that messages of certain topics were only circulated within a community of e-cigarette supporters, while other topics spread further, reaching more general Twitter users who may not support or use e-cigarettes.

Conclusions

Retweet networks can serve as proxy filters for marketing messages, as Twitter users decide which messages they will continue to diffuse among their followers. As certain e-cigarette messages extend beyond their point of origin, the audience being exposed expands beyond the e-cigarette community. Potential implications for health education campaigns include utilizing Twitter and targeting important gatekeepers or hubs that would maximize message diffusion.     

Comparative phylogeography and the identification of genetically divergent areas for conservation

Genetic diversity is recognized as a fundamental component of biodiversity and its protection is incorporated in several conventions and policies. However, neither the concepts nor the methods for assessing conservation value of the spatial distribution of genetic diversity have been resolved. Comparative phylogeography can identify suites of species that have a common history of vicariance. In this study we explore the strengths and limitations of Faith's measure of 'Phylogenetic Diversity' (PD) as a method for predicting from multiple intraspecific phylogeographies the underlying feature diversity represented by combinations of areas. An advantage of the PD approach is that information on the spatial distribution of genetic diversity can be combined across species and expressed in a form that allows direct comparison with patterns of species distributions. It also seeks to estimate the same parameter, feature diversity, regardless of the level of biological organization. We extend the PD approach by using Venn diagrams to identify the components of PD, including those unique to or shared among areas and those which represent homoplasy on an area tree or which are shared across all areas. PD estimation should be complemented by analysis of these components and inspection of the contributing phylogeographies. We illustrate the application of the approach using mtDNA phylogeographies from vertebrates resident in the wet tropical rainforests of north-east Queensland and compare the results to biodiversity assessments based on the distribution of endemic vertebrate species. The genetic vs. species approaches produce different assessments of conservation value, perhaps reflecting differences in the temporal and spatial scale of the determining processes. The two approaches should be seen as complementary and, in this case, conservation planning should incorporate information on both dimensions of biodiversity.     

Classification of the Adenylation and Acyl-Transferase Activity of NRPS and PKS Systems Using Ensembles of Substrate Specific Hidden Markov Models

There is a growing interest in the Non-ribosomal peptide synthetases (NRPSs) and polyketide synthases (PKSs) of microbes, fungi and plants because they can produce bioactive peptides such as antibiotics. The ability to identify the substrate specificity of the enzyme''s adenylation (A) and acyl-transferase (AT) domains is essential to rationally deduce or engineer new products. We here report on a Hidden Markov Model (HMM)-based ensemble method to predict the substrate specificity at high quality. We collected a new reference set of experimentally validated sequences. An initial classification based on alignment and Neighbor Joining was performed in line with most of the previously published prediction methods. We then created and tested single substrate specific HMMs and found that their use improved the correct identification significantly for A as well as for AT domains. A major advantage of the use of HMMs is that it abolishes the dependency on multiple sequence alignment and residue selection that is hampering the alignment-based clustering methods. Using our models we obtained a high prediction quality for the substrate specificity of the A domains similar to two recently published tools that make use of HMMs or Support Vector Machines (NRPSsp and NRPS predictor2, respectively). Moreover, replacement of the single substrate specific HMMs by ensembles of models caused a clear increase in prediction quality. We argue that the superiority of the ensemble over the single model is caused by the way substrate specificity evolves for the studied systems. It is likely that this also holds true for other protein domains. The ensemble predictor has been implemented in a simple web-based tool that is available at http://www.cmbi.ru.nl/NRPS-PKS-substrate-predictor/.     

Proximity-dependent inhibition in Escherichia coli isolates from cattle

We describe a novel proximity-dependent inhibition phenotype of Escherichia coli that is expressed when strains are cocultured in defined minimal media. When cocultures of "inhibitor" and "target" strains approached a transition between logarithmic and stationary growth, target strain populations rapidly declined >4 log CFU per ml over a 2-h period. Inhibited strains were not affected by exposure to conditioned media from inhibitor and target strain cocultures or when the inhibitor and target strains were incubated in shared media but physically separated by a 0.4-μm-pore-size membrane. There was no evidence of lytic phage or extracellular bacteriocin involvement, unless the latter was only present at effective concentrations within immediate proximity of the inhibited cells. The inhibitory activity observed in this study was effective against a diversity of E. coli strains, including enterohemorrhagic E. coli serotype O157:H7, enterotoxigenic E. coli expressing F5 (K99) and F4 (K88) fimbriae, multidrug-resistant E. coli, and commensal E. coli. The decline in counts of target strains in coculture averaged 4.8 log CFU/ml (95% confidence interval, 4.0 to 5.5) compared to their monoculture counts. Coculture of two inhibitor strains showed mutual immunity to inhibition. These results suggest that proximity-dependent inhibition can be used by bacteria to gain a numerical advantage when populations are entering stationary phase, thus setting the stage for a competitive advantage when growth conditions improve.     

Quantifying Discrepancies in Opinion Spectra from Online and Offline Networks

Online social media such as Twitter are widely used for mining public opinions and sentiments on various issues and topics. The sheer volume of the data generated and the eager adoption by the online-savvy public are helping to raise the profile of online media as a convenient source of news and public opinions on social and political issues as well. Due to the uncontrollable biases in the population who heavily use the media, however, it is often difficult to measure how accurately the online sphere reflects the offline world at large, undermining the usefulness of online media. One way of identifying and overcoming the online–offline discrepancies is to apply a common analytical and modeling framework to comparable data sets from online and offline sources and cross-analyzing the patterns found therein. In this paper we study the political spectra constructed from Twitter and from legislators'' voting records as an example to demonstrate the potential limits of online media as the source for accurate public opinion mining, and how to overcome the limits by using offline data simultaneously.     

Aging 2.0: Health Information about Dementia on Twitter

Online social media is widespread, easily accessible and attracts a global audience with a widening demographic. As a large proportion of adults now seek health information online and through social media applications, communication about health has become increasingly interactive and dynamic. Online health information has the potential to significantly impact public health, especially as the population gets older and the prevalence of dementia increases. However, little is known about how information pertaining to age-associated diseases is disseminated on popular social media platforms. To fill this knowledge gap, we examined empirically: (i) who is using social media to share information about dementia, (ii) what sources of information about dementia are promoted, and (iii) which dementia themes dominate the discussion. We data-mined the microblogging platform Twitter for content containing dementia-related keywords for a period of 24 hours and retrieved over 9,200 tweets. A coding guide was developed and content analysis conducted on a random sample (10%), and on a subsample from top users’ tweets to assess impact. We found that a majority of tweets contained a link to a third party site rather than personal information, and these links redirected mainly to news sites and health information sites. As well, a large number of tweets discussed recent research findings related to the prediction and risk management of Alzheimer’s disease. The results highlight the need for the dementia research community to harness the reach of this medium and its potential as a tool for multidirectional engagement.     

Does Twitter Trigger Bursts in Signature Collections?

Introduction

The quantification of social media impacts on societal and political events is a difficult undertaking. The Japanese Society of Oriental Medicine started a signature-collecting campaign to oppose a medical policy of the Government Revitalization Unit to exclude a traditional Japanese medicine, “Kampo,” from the public insurance system. The signature count showed a series of aberrant bursts from November 26 to 29, 2009. In the same interval, the number of messages on Twitter including the keywords “Signature” and “Kampo,” increased abruptly. Moreover, the number of messages on an Internet forum that discussed the policy and called for signatures showed a train of spikes.

Methods and Findings

In order to estimate the contributions of social media, we developed a statistical model with state-space modeling framework that distinguishes the contributions of multiple social media in time-series of collected public opinions. We applied the model to the time-series of signature counts of the campaign and quantified contributions of two social media, i.e., Twitter and an Internet forum, by the estimation. We found that a considerable portion (78%) of the signatures was affected from either of the social media throughout the campaign and the Twitter effect (26%) was smaller than the Forum effect (52%) in total, although Twitter probably triggered the initial two bursts of signatures. Comparisons of the estimated profiles of the both effects suggested distinctions between the social media in terms of sustainable impact of messages or tweets. Twitter shows messages on various topics on a time-line; newer messages push out older ones. Twitter may diminish the impact of messages that are tweeted intermittently.

Conclusions

The quantification of social media impacts is beneficial to better understand people’s tendency and may promote developing strategies to engage public opinions effectively. Our proposed method is a promising tool to explore information hidden in social phenomena.     

Identifying wildlife observations on twitter

Despite the potential of social media for environmental monitoring, concerns remain about the quality and reliability of the information automatically extracted. Notably there are many observations of wildlife on Twitter, but their automated detection is a challenge due to the frequent use of wildlife related words in messages that have no connection with wildlife observation. We investigate whether and what type of supervised machine learning methods can be used to create a fully automated text classification model to identify genuine wildlife observations on Twitter, irrespective of species type or whether Tweets are geo-tagged. We perform experiments with various techniques for building feature vectors that serve as input to the classifiers, and consider how they affect classification performance. We compare three classification approaches and perform an analysis of the types of features that are indicative for genuine wildlife observations on Twitter. In particular, we compare some classical machine learning algorithms, widely used in ecology studies, with state-of-the-art neural network models. Results showed that the neural network-based model Bidirectional Encoder Representations from Transformers (BERT) outperformed the classical methods. Notably this was the case for a relatively small training corpus, consisting of less than 3000 instances. This reflects that fact that the BERT classifier uses a transfer learning approach that benefits from prior learning on a very much larger collection of generic text. BERT performed particularly well even for Tweets that employed specialised language relating to wildlife observations. The analysis of possible indicative features for wildlife Tweets revealed interesting trends in the usage of hashtags that are unrelated to official citizen science campaigns. The findings from this study facilitate more accurate identification of wildlife-related data on social media which can in turn be used for enriching citizen science data collections.     

Uncovering Spatiotemporal Characteristics of Human Online Behaviors during Extreme Events

In response to an extreme event, individuals on social media demonstrate interesting behaviors depending on their backgrounds. By making use of the large-scale datasets of posts and search queries collected from Twitter and GoogleTrends, we first identify the distinct categories of human collective online concerns and durations based on the distributions of solo tweets and new incremental tweets about events. Such a characterization enables us to gain a better understanding of dynamic changes in human behaviors corresponding to different types of events. Next, we observe the heterogeneity of individual responses to events through measuring the fraction of event-related tweets relative to the tweets released by an individual, and thus empirically confirm the heterogeneity assumption as adopted in the meta-population models for characterizing collective responses to events. Finally, based on the correlations of information entropy in different regions, we show that the observed distinct responses may be caused by their different speeds in information propagation. In addition, based on the detrended fluctuation analysis, we find that there exists a self-similar evolution process for the collective responses within a region. These findings have provided a detailed account for the nature of distinct human behaviors on social media in presence of extreme events.     

Social Media,Public Participation,and the 2010 BP Deepwater Horizon Oil Spill

This research examines how information about an oil spill, its impacts, and the use of dispersants to treat the oil, moved through social media and the surrounding Internet during the 2010 BP Deepwater Horizon oil spill. Using a collection of tweets captured during the spill, we employ a mixed-method approach including an in-depth qualitative analysis to examine the content of Twitter posts, the connections that Twitter users made with each other, and the links between Twitter content and the surrounding Internet. This article offers a range of findings to help practitioners and others understand how social media is used by a variety of different actors during a slow-moving, long-term, environmental disaster. We enumerate some of the most salient themes in the Twitter data, noting that concerns about health impacts were more likely to be communicated in tweets about dispersant use, than in the larger conversation. We describe the accounts and behaviors of highly retweeted Twitter users, noting how locals helped to shape the network and the conversation. Importantly, our results show the online crowd wanting to participate in and contribute to response efforts, a finding with implications for future oil spill response.     

Research Blogging: Indexing and Registering the Change in Science 2.0

Increasing public interest in science information in a digital and 2.0 science era promotes a dramatically, rapid and deep change in science itself. The emergence and expansion of new technologies and internet-based tools is leading to new means to improve scientific methodology and communication, assessment, promotion and certification. It allows methods of acquisition, manipulation and storage, generating vast quantities of data that can further facilitate the research process. It also improves access to scientific results through information sharing and discussion. Content previously restricted only to specialists is now available to a wider audience. This context requires new management systems to make scientific knowledge more accessible and useable, including new measures to evaluate the reach of scientific information. The new science and research quality measures are strongly related to the new online technologies and services based in social media. Tools such as blogs, social bookmarks and online reference managers, Twitter and others offer alternative, transparent and more comprehensive information about the active interest, usage and reach of scientific publications. Another of these new filters is the Research Blogging platform, which was created in 2007 and now has over 1,230 active blogs, with over 26,960 entries posted about peer-reviewed research on subjects ranging from Anthropology to Zoology. This study takes a closer look at RB, in order to get insights into its contribution to the rapidly changing landscape of scientific communication.     

Situations in 140 Characters: Assessing Real-World Situations on Twitter

Over 20 million Tweets were used to study the psychological characteristics of real-world situations over the course of two weeks. Models for automatically and accurately scoring individual Tweets on the DIAMONDS dimensions of situations were developed. Stable daily and weekly fluctuations in the situations that people experience were identified. Predicted temporal trends were found, providing validation for this new method of situation assessment. On weekdays, Duty peaks in the midmorning and declines steadily thereafter while Sociality peeks in the evening. Negativity is highest during the workweek and lowest on the weekends. pOsitivity shows the opposite pattern. Additionally, gender and locational differences in the situations shared on Twitter are explored. Females share both more emotionally charged (pOsitive and Negative) situations, while no differences were found in the amount of Duty experienced by males and females. Differences in the situations shared from Rural and Urban areas were not found. Future applications of assessing situations using social media are discussed.     

Self-Organization on Social Media: Endo-Exo Bursts and Baseline Fluctuations

A salient dynamic property of social media is bursting behavior. In this paper, we study bursting behavior in terms of the temporal relation between a preceding baseline fluctuation and the successive burst response using a frequency time series of 3,000 keywords on Twitter. We found that there is a fluctuation threshold up to which the burst size increases as the fluctuation increases and that above the threshold, there appears a variety of burst sizes. We call this threshold the critical threshold. Investigating this threshold in relation to endogenous bursts and exogenous bursts based on peak ratio and burst size reveals that the bursts below this threshold are endogenously caused and above this threshold, exogenous bursts emerge. Analysis of the 3,000 keywords shows that all the nouns have both endogenous and exogenous origins of bursts and that each keyword has a critical threshold in the baseline fluctuation value to distinguish between the two. Having a threshold for an input value for activating the system implies that Twitter is an excitable medium. These findings are useful for characterizing how excitable a keyword is on Twitter and could be used, for example, to predict the response to particular information on social media.