基于VSM的电子作业反抄袭系统的设计与实现

摘要

针对日益严重的电子作业抄袭现象,在分析目前的电子作业抄袭检测系统无法将抄袭作业拒绝于提交之前等问题的基础上,阐述了一套基于空间向量模型TF-IDF方法的电子作业反抄袭系统.该系统在对电子作业进行分词的基础上,使用空间向量模型的TF-IDF方法计算文本相似度,并依据相似度判断电子作业是否有抄袭行为.为了解决因短时间内大量的电子作业提交而导致系统崩溃,系统使用MSMQ建立电子作业提交队列,同时,系统还提供了电子作业评阅及系统设置等功能.系统使用时间优先策略来认定抄袭作业,有效地从抄袭者和被抄袭者上杜绝了抄袭行为.%To solve the issue of increasingly severe e-homework plagiarism, an anti-plagiarism system of e-homework based on the vector space model (VSM) and TF-IDF is given, after the analysis of current counterparts systems. Similarity is calculated by VSM theory and TF-IDF after the segmentation of the e-homework, and plagiarism is decided by the similarity. Microsoft Message Queue (MSMQ) is used to relieve the stress of the system, and e-homework and system configuration functions are supported. Also time preference tragedy is used. And it can validly avoid the plagiarism from both copycat and the source.