| Year: 2006 | 
Download Free Adobe Acrobat Reader |
| LHNCBC-2006-075 |
| Semantic Representation of Consumer Questions and Physician Answers |
| Slaughter LA, Soergel D, Rindflesch TC |
| Int J Med Inform. 2006;75(7):513-29 |
| The aim of this study was to identify the under lying semantics of health consumers' questions and physicians' answers in order to analyze the semantic patterns within these texts. We manually identifed semantic relationships within question-answer pairs from Ask-the-Doctor Websites. Identifcation of the semantic relationship instances within the texts was based on the relationship classes and structure of the Unifed Medical Language System (UMLS) Semantic Network. We calculated the frequency of occurrence of each semantic relationship class, and conceptual graphs were generated, joining concepts together through the semantic relationships identifed. We then analyzed whether representations of physician's answers exactly matched the form of the question representations. Lastly, we examined characteristics of the answer conceptual graphs. We identifed 97 semantic relationship instances in thequestions and 334 instances in the answers. The most frequently identifed semantic relationship in both questions and answers was 'bringsabout' (causal). We found that the semantic relationship propositions identifed in answers that most frequently contain a concept also expressed in the question were: 'bringsabout', isa, 'co_occurs_with', 'diagnoses', and 'treats'. Using extracted semantic relationships from real-life questions and answers can produce a valuable analysis of the characteristics of these texts. This can lead to clues for creating semantic-based retrieval techniques that guide users to further information. For example, we determined that both consumers and physicians often express causative relationships and these play a key role in leading to further related concepts. |
| PDF |
