Assessing Content Diversity in Medical Weblogs

In this paper, we are considering weblogs focusing on medicine and health. Given this general topic, posts can deal with diseases, medical treatments, medications and the like to which in turn different aspects can be considered. Within a diversity-aware medical search engine knowledge about this kind of diversity can support grouping of search results into diversity dimensions covered by a text. Therefore, a method is introduced for studying topic and content diversity. The approach bases on information extraction technologies and domain knowledge and is applied to a set of medical weblog posts. The diversity of topics described in this dataset will be studied in more detail.