An Algorithm Research on Potential Problem Reactor in Medical Online Question Answering Community
Objective: Based on the online question-and-answer community of Internet medicine, a weighted user-personal model is proposed in view
of the pain point of the users' queries in the medical question-and-answer community which can not be effectively answered in time. Predicts
whether the recommended user can respond timely and effectively to the problem to improve the accuracy of the proposed results. .
Methods: Using the user's historical activity data in the community, a model of user's personal domain was proposed based on query-like
language model to describe the degree of user's concern in different field.
Results: In the experiment based on Baidu medical question-answering system data, compared with the existing algorithms, the potential
problem respondents in this paper have better recommendation effect.