Predicting the situational relevance of health web documents

Relevance is usually estimated by search engines using document content, disregarding the user behind the search and the characteristics of the task. In this work, we look at relevance as framed in a situational context, calling it situational relevance, and analyze if it is possible to predict it using documents, users and tasks characteristics. Using an existing dataset composed of health web documents, relevance judgments for information needs, user and task characteristics, we build a multivariate prediction model for situational relevance. Our model has an accuracy of 77.17%. Our findings provide insights into features that could improve the estimation of relevance by search engines, helping to conciliate the systemic and situational views of relevance. In a near future we will work on the automatic assessment of document, user and task characteristics.