Modeling the dynamics of personal expertise
Yi Fang, Archana Godavarthy · 2014
Personal expertise or interests often evolve over time. Despite much work on expertise retrieval in the recent years, very little work has studied the dynamics of personal expertise. In this paper, we propose a probabilistic model to characterize how people change or stick with their expertise. Specifically, three factors are taken into consideration in whether an expert will choose a new expertise area: 1) the personality of the expert in exploring new areas; 2) the similarity between the new area and the expert's current areas; 3) the popularity of the new area. These three factors are integrated into a unified generative process. A predictive language model is derived to estimate the distribution of the expert's words in her future publications. In addition, KL divergence is defined on the predictive language model to quantify and forecast the change of expertise. We conduct the experiments on a testbed of academic publications and the initial results demonstrate the effectiveness of the proposed approach.