دانلود رایگان ترجمه مقاله DOCODE 3.0 یک سیستم برای تشخیص سرقت ادبی با فرایند تلفیق اطلاعات – الزویر 2016

DOCODE 3.0 (شناساگر کپی اسناد): سیستمی برای تشخیص سرقت ادبی با استفاده از فرایند تلفیق اطلاعات از منابع داده های اسنادی مختلف

DOCODE 3.0 (DOcument COpy DEtector): A system for plagiarism detection by applying an information fusion process from multiple documental data sources

Abstract

Plagiarism refers to the act of presenting external words, thoughts, or ideas as one’s own, without providing references to the sources from which they were taken. The exponential growth of different digital document sources available on the Web has facilitated the spread of this practice, making the accurate detection of it a crucial task for educational institutions. In this article, we present DOCODE 3.0, a Web system for educational institutions that performs automatic analysis of large quantities of digital documents in relation to their degree of originality. Since plagiarism is a complex problem, frequently tackled at different levels, our system applies algorithms in order to perform an information fusion process from multi data source to all these levels. These algorithms have been successfully tested in the scientific community in solving tasks like the identification of plagiarized passages and the retrieval of source candidates from the Web, among other multi data sources as digital libraries, and have proven to be very effective. We integrate these algorithms into a multi-tier, robust and scalable JEE architecture, allowing many different types of clients with different requirements to consume our services. For users, DOCODE produces a number of visualizations and reports from the different outputs to let teachers and professors gain insights on the originality of the documents they review, allowing them to discover, understand and handle possible plagiarism cases and making it easier and much faster to analyze a vast number of documents. Our experience here is so far focused on the Chilean situation and the Spanish language, offering solutions to Chilean educational institutions in any of their preferred Virtual Learning Environments. However, DOCODE can easily be adapted to increase language coverage.

1. Introduction

Today’s scenario shows a significant change in the way of accessing information, emphasizing the use of the Web as one of the main sources of knowledge [48,49]. However, access to the Web has been cited as one of the main reasons for the perceived decline in academic integrity, particularly in relation to plagiarism [44]. Plagiarism basically consists of taking others’ work and labeling it as one’s own. Likewise, text plagiarism is defined as the action of copying someone else’s writings without the proper citation. When applied to the educational environment, we also find that the term student plagiarism is often used to refer to the incidences of plagiarism committed by students who attend educational institutions [20], which mainly represent cases of text plagiarism. In this context, because there is a vast amount of easy-to-access information, the plagiarism phenomenon has been becoming more popular and easier to resort to. International studies demonstrate the magnitude of this behavior, with a high percentage of students who reported to be using the Web as a major source of plagiarism [29]. In [38], Posner recently estimated that one-third of all high school and college students have committed some kind of plagiarism. The situation in Chile is not different. A 2010 survey carried out by the Department of Industrial Engineering of the University of Chile, showed that about 55% of middle school students and 42% of higher education students declared having copied information without citing the source [31]. Given the large volume of documents and information sources that exist today, originality examination and plagiarism detection are becoming increasingly more complex tasks. While Web search engines can be used to detect Internet plagiarism, the detection process is, by any standards, both tedious and labor-intensive [20]. In today’s scenario, a manual examination appears as an extremely time-consuming process and a virtually impossible task; teachers often do not have the necessary time for exhaustive reviews. Also, some students will continue to plagiarize regardless of how hard tutors try to stop them [22]. In the Chilean case, the absence of a suitable plagiarism detection system in Spanish contributes to making the situation we have described above even more alarming. Plagiarism is an important issue for educational purposes at every level, because it could affect a student’s learning process [27]. Teachers and academics abhor plagiarism because it is inconsistent with pedagogical aims. As a result there has been a desire on the part of teachers to attack the problem by developing different measures to detect the originality of the work submitted by the students [44]. Looking at the extent of the problem, [16] concludes that it is quite obvious that academia requires tools to automate and enhance plagiarism detection. These tools, often called plagiarism detection engines, are software that compare documents with possible sources in order to identify similarity and so discover submissions that might be plagiarized [12], making it easier for teachers to analyze a vast number of documents. A review of the literature about plagiarism in educational institutions shows that many authors have proposed that it is a set of distinct inappropriate behaviors rather than only a single problem. In an effort to tackle this complexity, some of these authors have actually proposed different levels or types of plagiarism, generating subproblems that might be easier to analyze. From our perspective, when referring to educational purposes, plagiarism detection engines are supposed to offer professors a set of tools to gain insights about the documents that are reviewed, rather than simply checking plagiarism cases, thus tackling the problem of plagiarism from all the perspectives existing in literature. Therefore, our work presents a system that performs automated textual plagiarism detection for educational institutions using a multi-level perspective. Our system, called DOCODE 3.0 (DOcument COpy DEtector 3.0),1 cooperates with teachers and professors offering them a complete interface with visual tools to discover, understand and handle different plagiarism levels and cases. DOCODE is a full-featured system based on a solid, scalable architecture and implementing a set of algorithms for plagiarism detection that have successfully proven to be effective, in some cases, even outperforming state-of-the-art approaches in literature. These results were validated in multiple previous publications and in international plagiarism detection competitions. Although our experience is so far limited to the Chilean situation and the Spanish language, most of our algorithms are not language dependent, so DOCODE can easily be adapted to increase language coverage. The rest of this paper is structured as follows. Below in Section 2, we review related work regarding the plagiarism topic and also present some of the most important state-of-the-art plagiarism detection algorithms and frameworks. Then, in Section 3, we explain how DOCODE works and what kind of services it provides. Also, the main algorithms underlying the system are presented. Section 4 shows how DOCODE is structured, explaining its architecture. Later, Section 5 introduces our user interfaces. Finally, Section 6 presents conclusions and proposed future work.