@article{152,
  author = {Kerstin Denecke},
  title = {Diversity in Medical Social Media Data: Approaches, Study and Future Challenges},
  journal = {International Journal of Computational Linguistics Research},
  year = {2010},
  volume = {1},
  number = {1},
  doi = {},
  url = {http://www.dline.info/jisr/fulltext/v1n1/3.pdf},
  abstract = {Medical social media data offers an additional source of information on medical issues. Web 2.0 or Medicine 2.0, respectively, open new ways in providing and accessing this information. The medical content available is highly diverse: It can deal with diseases, medical treatments, medications and the like to which in turn different aspects can be considered. Presented content can rather deal with experiences or can provide informative insights into a topic. Making this diversity visible to a user could among others help to recognise unknown facets of a topic or help to get an overview on the information content of specific data sources. The objective of this work is to introduce the problem of diversity of medical Web content and to present a variety of methods for identifying and analysing content diversity in this data. The approaches base on information extraction technologies and involve domain knowledge. They are applied to a set of medical social media data for which the content diversity is studied. Furthermore, it will be shown how diversity information related to the subjectivity can be used for ranking to improve user satisfaction.},
}