A computational narrative construction method with applications in organizational learning of social service organizations

摘要

Acquisition of knowledge must be interwoven with the process of applying it. However, traditional training methods which provide abstract knowledge have shown ineffective for gaining experience of the work. In order to solve this problem, more and more researchers have included narrative in simulation, which is known as narrative simulation. By providing the narratives, participants recognize the choices, decisions, and experience that lead to the consequences of those decisions. It has been proven that narrative simulation is very useful in facilitating in-depth learning and reflective learning. However, conventional methods of data collection and narrative construction for narrative simulation are labor intensive and time consuming. They make use of previous narratives manually and directly. They are inadequate to cope with the fast moving world where knowledge is changing rapidly. In order to provide a way for facilitating the construction of narrative simulation, a novel computational narrative construction method is proposed. By incorporating technologies of knowledge-based system (KBS), computational linguistics, and artificial intelligence (AI), the proposed method provides an efficient and effective way for collecting narratives and automating the construction of narratives. The method converts the unstructured narratives into a structural representation for abstraction and facilitating computing processing. Moreover, it constructs the narratives that combine multiple narratives into a single narrative by applying a forecasting algorithm. The proposed method was successfully implemented in early intervention in mental health care of a social service company in Hong Kong since the case records in that process have structural similarities to narrative. The accuracies of data conversion and predictive function were measured based on recall and precision and encouraging results were obtained. High recall and precision are achieved in the data conversion function, and high recall for the predictive function when new concepts are excluded. The results show that it is possible for converting multiple narratives into a single narrative automatically. Based on the approach, it helps to stimulate knowledge workers to explore new problem solving methods so as to increase the quality of their solutions.