Automatic detecting quality criteria on health web pages

Quality and transparency of information on the web is one of major issues in the medical and patient safety area. HON foundation has defined a set of eight ethical principles which correspond to the first step in quality control of medical websites. Network of experts is working in order to manually define if a given website satisfies required principles. As amount of information on the web is going increasingly, manual expertise becomes unsufficient and automatic systems should be used in order to help medical experts. In this paper we present design and evaluation of automatic system conceived for the categorisation of medical and health documents according to HONcode ethical principles. We justify different choices made when designing the system. First evaluation shows promising results. Currently the system shows 0.78 of micro precision and 0.73 of F-measure, with 0.06 of errors. Several improvements remain a perspective to this