Surveillance of communicable diseases using social media: A systematic review.

BACKGROUND: Communicable diseases pose a severe threat to public health and economic growth. The traditional methods that are used for public health surveillance, however, involve many drawbacks, such as being labor intensive to operate and resulting in a lag between data collection and reporting. To effectively address the limitations of these traditional methods and to mitigate the adverse effects of these diseases, a proactive and real-time public health surveillance system is needed. Previous studies have indicated the usefulness of performing text mining on social media. OBJECTIVE: To conduct a systematic review of the literature that used textual content published to social media for the purpose of the surveillance and prediction of communicable diseases. METHODOLOGY: Broad search queries were formulated and performed in four databases. Both journal articles and conference materials were included. The quality of the studies, operationalized as reliability and validity, was assessed. This qualitative systematic review was guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. RESULTS: Twenty-three publications were included in this systematic review. All studies reported positive results for using textual social media content to surveille communicable diseases. Most studies used Twitter as a source for these data. Influenza was studied most frequently, while other communicable diseases received far less attention. Journal articles had a higher quality (reliability and validity) than conference papers. However, studies often failed to provide important information about procedures and implementation. CONCLUSION: Text mining of health-related content published on social media can serve as a novel and powerful tool for the automated, real-time, and remote monitoring of public health and for the surveillance and prediction of communicable diseases in particular. This tool can address limitations related to traditional surveillance methods, and it has the potential to supplement traditional methods for public health surveillance.

Brands, networks, communities: How brand names are wired in the mind.

Brands can be defined as psychological constructs residing in our minds. By analyzing brand associations, we can study the mental constructs around them. In this paper, we study brands as parts of an associative network based on a word association database. We explore the communities-closely-knit groups in the mind-around brand names in this structure using two community detection algorithms in the Hungarian word association database ConnectYourMind. We identify brand names inside the communities of a word association network and explain why these brand names are part of the community. Several detected communities contain brand names from the same product category, and the words in these categories were connected either to brands in the category or to words describing the product category. Based on our findings, we describe the mental position of brand names. We show that brand knowledge, product knowledge and real word knowledge interact with each other. We also show how the meaning of a product category arises and how this meaning is related to brand meaning. Our results suggest that words sharing the same community with brand names can be used in brand communication and brand positioning.

Using Machine Learning for Pharmacovigilance: A Systematic Review.

Pharmacovigilance is a science that involves the ongoing monitoring of adverse drug reactions to existing medicines. Traditional approaches in this field can be expensive and time-consuming. The application of natural language processing (NLP) to analyze user-generated content is hypothesized as an effective supplemental source of evidence. In this systematic review, a broad and multi-disciplinary literature search was conducted involving four databases. A total of 5318 publications were initially found. Studies were considered relevant if they reported on the application of NLP to understand user-generated text for pharmacovigilance. A total of 16 relevant publications were included in this systematic review. All studies were evaluated to have medium reliability and validity. For all types of drugs, 14 publications reported positive findings with respect to the identification of adverse drug reactions, providing consistent evidence that natural language processing can be used effectively and accurately on user-generated textual content that was published to the Internet to identify adverse drug reactions for the purpose of pharmacovigilance. The evidence presented in this review suggest that the analysis of textual data has the potential to complement the traditional system of pharmacovigilance.

Socioeconomic and environmental patterns behind H1N1 spreading in Sweden.

Identifying the critical factors related to influenza spreading is crucial in predicting and mitigating epidemics. Specifically, uncovering the relationship between epidemic onset and various risk indicators such as socioeconomic, mobility and climate factors can reveal locations and travel patterns that play critical roles in furthering an outbreak. We study the 2009 A(H1N1) influenza outbreaks in Sweden's municipalities between 2009 and 2015 and use the Generalized Inverse Infection Method (GIIM) to assess the most significant contributing risk factors. GIIM represents an epidemic spreading process on a network: nodes correspond to geographical objects, links indicate travel routes, and transmission probabilities assigned to the links guide the infection process. Our results reinforce existing observations that the influenza outbreaks considered in this study were driven by the country's largest population centers, while meteorological factors also contributed significantly. Travel and other socioeconomic indicators have a negligible effect. We also demonstrate that by training our model on the 2009 outbreak, we can predict the epidemic onsets in the following five seasons with high accuracy.

Inferring the risk factors behind the geographical spread and transmission of Zika in the Americas.

BACKGROUND: An unprecedented Zika virus epidemic occurred in the Americas during 2015-2016. The size of the epidemic in conjunction with newly recognized health risks associated with the virus attracted significant attention across the research community. Our study complements several recent studies which have mapped epidemiological elements of Zika, by introducing a newly proposed methodology to simultaneously estimate the contribution of various risk factors for geographic spread resulting in local transmission and to compute the risk of spread (or re-introductions) between each pair of regions. The focus of our analysis is on the Americas, where the set of regions includes all countries, overseas territories, and the states of the US. METHODOLOGY/PRINCIPAL FINDINGS: We present a novel application of the Generalized Inverse Infection Model (GIIM). The GIIM model uses real observations from the outbreak and seeks to estimate the risk factors driving transmission. The observations are derived from the dates of reported local transmission of Zika virus in each region, the network structure is defined by the passenger air travel movements between all pairs of regions, and the risk factors considered include regional socioeconomic factors, vector habitat suitability, travel volumes, and epidemiological data. The GIIM relies on a multi-agent based optimization method to estimate the parameters, and utilizes a data driven stochastic-dynamic epidemic model for evaluation. As expected, we found that mosquito abundance, incidence rate at the origin region, and human population density are risk factors for Zika virus transmission and spread. Surprisingly, air passenger volume was less impactful, and the most significant factor was (a negative relationship with) the regional gross domestic product (GDP) per capita. CONCLUSIONS/SIGNIFICANCE: Our model generates country level exportation and importation risk profiles over the course of the epidemic and provides quantitative estimates for the likelihood of introduced Zika virus resulting in local transmission, between all origin-destination travel pairs in the Americas. Our findings indicate that local vector control, rather than travel restrictions, will be more effective at reducing the risks of Zika virus transmission and establishment. Moreover, the inverse relationship between Zika virus transmission and GDP suggests that Zika cases are more likely to occur in regions where people cannot afford to protect themselves from mosquitoes. The modeling framework is not specific for Zika virus, and could easily be employed for other vector-borne pathogens with sufficient epidemiological and entomological data.