The International Biosecurity Intelligence System uses a combination of automation and crowdsourcing* to collect and classify information which can be then used to produce biosecurity intelligence.
The automated aspect involves a software robot that scours the internet every day looking for plant and animal disease reports, industry reports, articles from relevant journals, and any other articles or comments that may be relevant to biosecurity. Resources such as search engines, RSS feeds and Twitter are scanned. Once an article is found, 3rd party web services including AlchemyAPI and GeoNames are used to extract information from the article such as the title, text, author, language and locations. If necessary, articles are translated to English using Bing Translator or Google Translate.
The crowdsourced aspect involves engaging the IBIS community to perform two main tasks:
- Evaluate whether an article collected by the robot is relevant to the site or not.
- Edit the article and ensure that it’s been categorised and tagged correctly, that the publish date and places are correct, and so on.
* “Crowdsourcing is the practice of obtaining needed services, ideas, or content by soliciting contributions from a large group of people, and especially from an online community, rather than from traditional employees or suppliers” (http://www.merriam-webster.com/dictionary/crowdsourcing). Access here more information on crowdsourcing.
- Member: receives a (personalised) daily digest, can search the database, add comments to articles, submit articles to the community.
- Article Evaluator (AE): in addition to the member’s rights, the AE can also evaluate the articles therefore changing their status (see below), edit their content, promote them or alert the community, assign articles to issues.
- Search Editor (SE): can create search queries, can add and edit: search sources, pests, diseases, hosts, qualifiers and blocked sites.
Click here to jump straight to the IBIS community page.
Each article in IBIS has a status, indicating its relevance and importance. There are 5 statuses: Trash, Raw, Keep, Promoted and Alert. Each has a unique colour and icon. The diagram below shows the 5 different statuses an article can have within the IBIS system, and how these are related.