Ed de Quincey

Early Warning and Outbreak Detection Using Social Networking Websites: The Potential of Twitter

Epidemic Intelligence is being used to gather information about potential diseases outbreaks from both formal and increasingly informal sources. A potential addition to these informal sources are social networking sites such as Facebook and Twitter. In this paper we describe a method for extracting messages, called “tweets” from the Twitter website and the results of a pilot study which collected over 135,000 tweets in a week during the current Swine Flu pandemic.

Overview of e-Bug: an antibiotic and hygiene educational resource for schools

Antibiotic resistance is an increasing community problem and is related to antibiotic use. If antibiotic use could be reduced, the tide of increasing resistance could be stemmed. e-Bug is a European project involving 18 European countries, partly funded by The Directorate-General for Health and Consumers (DG SANCO) of the European Commission. It aims to develop and disseminate across Europe a junior and senior school teaching pack and web site (hosting the lesson plans and complementary games) that teach young people about prudent antibiotic use, microbes, transmission of infection, hygiene and vaccines. The aim of e-Bug is to increase young peoples understanding, through enjoyable activities, of why it is so important to use antibiotics correctly in order to control antibiotic resistance, and to have good hand and respiratory hygiene to help reduce the spread of infection. Within the senior school pack the sexual transmission of infections has also been included, as the peak age of chlamydial infection is in 16-24 year olds. Teachers, young people and the consortium of 18 countries were closely involved with agreeing learning outcomes and developing the resource activities. Young people helped create the characters and microbe artwork. The resources have been translated, adapted for and disseminated to schools across 10 countries in Europe, and endorsed by the relevant government departments of health and education. The web site has been accessed from >200 countries. The resources will be translated into all European Union languages, and have been used to promote European Antibiotic Awareness Day and better hand and respiratory hygiene during the influenza pandemic in 2009.

#Swineflu: Twitter predicts swine flu outbreak in 2009

Early warning systems for the identification and tracking of infections disease outbreaks have become an important tool in the field of epidemiology. While government lead initiatives to increase the sharing of surveillance data have improved early detection and control, along with advanced web monitoring and analytics services, the recent swine flu outbreak of 2009 demonstrated the important role social media has and the wealth of data it exposes. In this paper, we present an investigation into Twitter, using around 3 Million tweets gathered between May and December 2009, as a possible source of surveillance data and its feasibility to serve as an early warning system. By performing simple filtering and normalization, we demonstrate that Twitter can serve as a self-reporting tool, and hence, provide indications of increased infection spreading. Our initial findings indicate that Twitter can detect such events up to one week before conventional GP reported surveillance data.

What are school children in Europe being taught about hygiene and antibiotic use

e-Bug is a pan-European antibiotic and hygiene teaching resource that aims to reinforce awareness in school children of microbes, prudent antibiotic use, hygiene and the transmission of infection. Prior to the production of the resource, it was essential to examine the educational structure across each partner country and assess what school children were being taught on these topics. A questionnaire was devised for distribution to each European partner (Belgium, Czech Republic, Denmark, England, France, Greece, Italy, Poland, Portugal and Spain), exploring their educational structure and examining educational resources or campaigns currently available. From the data collected it was evident that the majority of European schools have structured hand hygiene practices in place from a young age. The curricula in all countries cover the topic of human health and hygiene, but limited information is provided on antibiotics and their prudent use. School educational resources that link to the national curriculum and implement National Advice to the Public campaigns in the classroom are limited. The Microbes en question mobile health education campaign in France is an example of a successful childrens education campaign and an innovative programme. Evaluation of the impact of school education on attitude and change of behaviour is also limited throughout many European countries. Not enough is currently being done across Europe to educate school children on the importance of appropriate antibiotic use and antibiotic resistance. The data from this research were used to develop e-Bug, a European Union-funded antibiotic and hygiene teaching resource.

Development of an educational resource on microbes, hygiene and prudent antibiotic use for junior and senior school children

Health promotion interventions aimed at children and young people have the potential to lay the foundations for healthy lifestyles. One such intervention, e-Bug, aims to provide schoolchildren with knowledge of prudent antibiotic use and how to reduce the spread of infection. Many children and schools approach learning in different ways; therefore, it is essential to research school needs and the variety of learning styles when creating any school resources. This article outlines the process involved during the development of a pan-European educational resource, and identifies the final pack layout, based on feedback from teacher focus groups, student questionnaires and European partner discussions.

A critical analysis of studies that address the use of text mining for citation screening in systematic reviews

Background: Since the introduction of the systematic review process to Software Engineering in 2004, researchers have investigated a number of ways to mitigate the amount of effort and time taken to filter through large volumes of literature. Aim: This study aims to provide a critical analysis of text mining techniques used to support the citation screening stage of the systematic review process. Method: We critically re-reviewed papers included in a previous systematic review which addressed the use of text mining methods to support the screening of papers for inclusion in a review. The previous review did not provide a detailed analysis of the text mining methods used. We focus on the availability in the papers of information about the text mining methods employed, including the description and explanation of the methods, parameter settings, assessment of the appropriateness of their application given the size and dimensionality of the data used, performance on training, testing and validation data sets, and further information that may support the reproducibility of the included studies. Results: Support Vector Machines (SVM), Naïve Bayes (NB) and Committee of classifiers (Ensemble) are the most used classification algorithms. In all of the studies, features were represented with Bag-of-Words (BOW) using both binary features (28%) and term frequency (66%). Five studies experimented with n-grams with n between 2 and 4, but mostly the unigram was used. χ2, information gain and tf-idf were the most commonly used feature selection techniques. Feature extraction was rarely used although LDA and topic modelling were used. Recall, precision, F and AUC were the most used metrics and cross validation was also well used. More than half of the studies used a corpus size of below 1,000 documents for their experiments while corpus size for around 80% of the studies was 3,000 or fewer documents. The major common ground we found for comparing performance assessment based on independent replication of studies was the use of the same dataset but a sound performance comparison could not be established because the studies had little else in common. In most of the studies, insufficient information was reported to enable independent replication. The studies analysed generally did not include any discussion of the statistical appropriateness of the text mining method that they applied. In the case of applications of SVM, none of the studies report the number of support vectors that they found to indicate the complexity of the prediction engine that they use, making it impossible to judge the extent to which over-fitting might account for the good performance results. Conclusions: There is yet to be concrete evidence about the effectiveness of text mining algorithms regarding their use in the automation of citation screening in systematic reviews. The studies indicate that options are still being explored, but there is a need for better reporting as well as more explicit process details and access to datasets to facilitate study replication for evidence strengthening. In general, the reader often gets the impression that text mining algorithms were applied as magic tools in the reviewed papers, relying on default settings or default optimization of available machine learning toolboxes without an in-depth understanding of the statistical validity and appropriateness of such tools for text mining purposes.

eBug - teaching children hygiene principles using educational games

Technology enhanced education has been recently established as a new approach for all stages of education. However, among these new IT media it is computer games playing the central role in delivering education in particular to children and teenagers, however, real world sound evaluation is often given little attention. The EU funded e-Bug project developed web games aimed at children to teach basic principles of prudent antibiotics use, hand and respiratory hygiene and aims to reinforces an awareness of microbes, hand and respiratory hygiene among junior and senior school children in 10 countries in Europe. An educational pack implemented in schools across Europe is complemented by Internet web games for two age groups teaching a set of learning objectives (LOs) using a fast and interactive platform game design for junior children and investigate detective games based on PBL principles for senior children. In this paper, we present the design of e-Bug junior and senior games and evaluation results.

Follow #eHealth2011: Measuring the Role and Effectiveness of Online and Social Media in Increasing the Outreach of a Scientific Conference

Background Social media promotion is increasingly adopted by organizers of industry and academic events; however, the success of social media strategies is rarely questioned or the real impact scientifically analyzed. Objective We propose a framework that defines and analyses the impact, outreach, and effectiveness of social media for event promotion and research dissemination to participants of a scientific event as well as to the virtual audience through the Web. Methods Online communication channels Twitter, Facebook, Flickr, and a Liveblog were trialed and their impact measured on outreach during five phases of an eHealth conference: the setup, active and last-minute promotion phases before the conference, the actual event, and after the conference. Results Planned outreach through online channels and social media before and during the event reached an audience several magnitudes larger in size than would have been possible using traditional means. In the particular case of eHealth 2011, the outreach using traditional means would have been 74 attendees plus 23 extra as sold proceedings and the number of downloaded articles from the online proceedings (4107 until October 2013). The audience for the conference reached via online channels and social media was estimated at more than 5300 in total during the event. The role of Twitter for promotion before the event was complemented by an increased usage of the website and Facebook during the event followed by a sharp increase of views of posters on Flickr after the event. Conclusions Although our case study is focused on a particular audience around eHealth 2011, our framework provides a template for redefining “audience” and outreach of events, merging traditional physical and virtual communities and providing an outline on how these could be successfully reached in clearly defined event phases.

The use of social bookmarking by health care students to create communities of practice

Teaching and learning health and social care in a digital age produces many challenges for students and their teachers. A common hurdle for healthcare students and practitioners is the sheer amount of information that they have to make sense of. Another challenge is where this information is captured and stored, with people utilising personal, as well as institutionally owned devices. A potential solution to these problems is the use of social bookmarking applications such as “delicious”, where users can create a centralised repository of online resources, share them with other users, and view what others are bookmarking. This paper describes research conducted at the University of Greenwich involving 160 participants across three Schools and 5 modules, including Health and Social Care who were encouraged to integrate social bookmarking into their learning and teaching. Participants were instructed to tag their resources with an appropriate module code tag e.g. NURS1297 so that a repository of module specific bookmarks was created. Over a 4 month period, 160 users created 1430 bookmarks with 5032 tags. Further analysis of the bookmarking behaviour is discussed along with reflections on the suitability of social bookmarking to create digitally literate health care communities of practice.

Using supervised machine learning algorithms to detect suspicious URLs in online social networks

The increasing volume of malicious content in social networks requires automated methods to detect and eliminate such content. This paper describes a supervised machine learning classification model that has been built to detect the distribution of malicious content in online social networks (ONSs). Multisource features have been used to detect social network posts that contain malicious Uniform Resource Locators (URLs). These URLs could direct users to websites that contain malicious content, drive-by download attacks, phishing, spam, and scams. For the data collection stage, the Twitter streaming application programming interface (API) was used and VirusTotal was used for labelling the dataset. A random forest classification model was used with a combination of features derived from a range of sources. The random forest model without any tuning and feature selection produced a recall value of 0.89. After further investigation and applying parameter tuning and feature selection methods, however, we were able to improve the classifier performance to 0.92 in recall.