Identifying Key People in Chinese Literary Works Using e-Core Decomposition

IEEE ACCESS(2020)

引用 0|浏览4
暂无评分
摘要
The plots of many literary works are very complex, which hinders the readers' comprehension of these literary works. Thus, to help readers' comprehension of complex literary works, tools should be proposed to support their comprehension by presenting the most important information to readers. In the case of literary works, the most important information may be the most important people, also called the key people. Key people play an important role in promoting the development of the plot of literary works. Thus, identifying key people helps to simplify readers' comprehension of literary works. The traditional way to comprehend literary works mainly depends on intensive reading, and no previous work has been done to explore the problem of key people identification in literary works. In this paper, we define the concept of key people and propose an approach, IPWC, to Identify key People in Chinese literary Works using e-Core decomposition. First, it uses theWeighted People co-occurrence Network (WPN) to represent people and their coupling relationships, and the frequency of the relationship. Second, an e-core decomposition is proposed and applied to decompose the WPN into shells and obtain the coreness of each people. Finally, all the people are sorted in a descending order according to their coreness, and the top-ranked people are the key people identified by our approach. The empirical experiments performed on a famous Chinese literary work, The History of the Three Kingdoms, show that WPN has small world and scale-free features. Furthermore, our approach is feasible and more effective than other compared approaches. Our approach can be used to build an automatic tool that can identify the key people for readers to aid their comprehension of a Chinese literary work.
更多
查看译文
关键词
Literary work comprehension,social network,culture analysis,key people,e-core decomposition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要