Title: Modeling of Authors' Writing Styles to Detect Plagiarism in Japanese Academic Reports

Year of Publication: Nov - 2018
Page Numbers: 29-35
Authors: Asako Ohno, Asako Ohno, Takahiro Yamasaki, Kin-ichiroh Tokiwa, Kazuhide Togai
Conference Name: The Fourth International Conference on Electronics and Software Science (ICESS2018)
- Japan

Abstract:


In recent years, it has become easier for students to obtain well-written reports from the Internet in short time, or copy and paste the contents of their classmates' reports into their reports. Consequently, plagiarism that students engage in is becoming a primary issue that interferes with the provision of fair grading by teachers. In some cases, students plagiarize unintentionally. Thus, it is important for teachers to detect plagiarism with careful attention to coincidental similarity. In this study, we introduce a plagiarism detection method focusing on authors' writing style in academic reports written in the Japanese language, which consists of different types of characters. This method detects plagiarism according to the author's writing style, which is represented by a number of Hidden Markov Models called writing models. First, we overview and summarize various kinds of academic plagiarism and discuss the difficulties of executing plagiarism detection; then, we explain our proposed method, and report our attempt to detect plagiarism with our method. We also examine the models' ability to represent writing style features through investigation on parameters of writing models.