Bridging Text Mining and Bayesian Networks

Abstract

Bayesian networks need to be updated as and when new data is observed. Literature mining is a very important source of this new data after the initial network is constructed using the expert’s knowledge. In this work, we specifically interested in the causal associations and experimental results obtained from literature mining. However, these associations and numerical results cannot be directly integrated with the Bayesian network. The source of the literature and the perceived quality of research needs to be factored into the process of integration, just like a human, reading the literature, would. We present a general methodology for deriving a confidence measure for the mined data and provide inputs to the expert for resolving the modeling issues in integrating it with the existing network.