1,721,060 research outputs found
Detecting the Usage of Large Language Models Exploiting Generative Adversarial Networks
No full textThe adoption of Large Language Models (LLMs) in the education context has been strongly increasing in the last years. A large range of possible applications shows the great opportunities derived from the use of LLM for learning and teaching tasks. However, LLM also introduces the risk that cheating students use existing tools to generate academic content, making it extremely difficult for the teacher to evaluate his/her performance. This drives a great interest in researchers and developers to study new approaches for distinguishing generated content from human content. However, the existing approaches are not able to adapt to the rapid improvement and evolution of content generators that have always been more effective in simulating human tasks. Starting from these considerations this paper proposes a new approach ensuring a great capability to adapt to the continuous generator market changes thanks to the adoption of generative adversarial networks (GANs). The proposed approach includes a generator that starting from the human-written content can obtain new generated content leveraging a continuous retraining process. The proposed approach is evaluated on a dataset composed of 150k human-written and LLM-generated texts. It is built starting from a free available dataset. The empirical validation shows good performance of the proposed approach to discriminate the contents obtaining an accuracy of 0.86
Knowledge Management Integrated with E-Learning in Open Innovation
No full textThis paper presents a framework aiming to support an «innovation chain» in an Open Innovation (OI) perspective. In order to transfer research results from producers to users, it is necessary to develop a Knowledge Manage-ment System supporting formalization, packaging and characterization to
be able to select, understand and collect research results and/or innovations deriving from them. Suitable skills are required to transfer and collect innovation. Since in OI the knowledge producer and fi nal users are by defi nition geographically distant, the required specialist skills have to be
acquired through an e-learning system. This system must offer Learning Objects that can be combined within a course that also takes into account the user’s past experiences. This work proposes an approach based on the integration of these two systems, and presents PROMETHEUS, a tool supporting this approach. The results of preliminary experimentation highlighted the strengths and weaknesses of the approach. They will be used to plan further experimentation and initiatives serving to facilitate the transfer of research results from state of the art to state of practice
Software Analytics to Support Students in Object-Oriented Programming Tasks: An Empirical Study
Full text linkThe computing education community has shown a long-time interest in how to analyze the Object-Oriented (OO) source code developed by students to provide them with useful formative tips. Instructors need to understand the student's difficulties to provide precise feedback on most frequent mistakes and to shape, design and effectively drive the course. This paper proposes and evaluates an approach allowing to analyze student's source code and to automatically generate feedback about the more common violations of the produced code. The approach is implemented through a cloud-based tool allowing to monitor how students use language constructs based on the analysis of the most common violations of the Object-Oriented paradigm in the student source code. Moreover, the tool supports the generation of reports about student's mistakes and misconceptions that can be used to improve the students' education. The paper reports the results of a quasi-experiment performed in a class of a CS1 course to investigate the effects of the provided reports in terms of coding ability (concerning the correctness and the quality of the produced source code). Results show that after the course the treatment group obtained higher scores and produced better source code than the control group following the feedback provided by the teachers
Towards automatic assessment of object-oriented programs
No full textThe computing education community has shown a long-time interest in how to analyze the Object-Oriented (OO) source codedeveloped by students to provide them with useful formative tips.In this paper, we propose and evaluate an approach to analyzehow students use Java and its language constructs. The approach isimplemented through a cloud-based integrated development environment (IDE) and it is based on the analysis of the most commonviolations of the OO paradigm in the student source code. Moreover,the IDE supports the automatic generation of reports about student's mistakes and misconceptions that can be used by instructorsto improve the course design. The paper discusses the preliminaryresults of an experiment performed in a class of a Programming IIcourse to investigate the effects of the provided reports in terms ofcoding ability (concerning the correctness of the produced code)
Distributed Software Development with Knowledge Experience Packages
No full textIn software production process, a lot of knowledge is created and remain silent. Therefore, it cannot be reused to improve the effectiveness and the efficiency of these processes. This problem is amplified in the case of a distributed production. In fact, distributed software development requires complex context specific knowledge regarding the particularities of different technologies, the potential of existing software, the needs and expectations of the users. This knowledge, which is gained during the project execution, is usually tacit and is completely lost by the company when the production is completed. Moreover, each time a new production unit is hired, despite the diversity of culture and capacity of people, it is necessary to standardize the working skills and methods of the different teams if the company wants to keep the quality level of processes and products. In this context, we used the concept of Knowledge Experience Package (KEP), already specified in previous works and the tool realized to support KEP approach. In this work, we have carried out an experiment in an industrial context in which we compared the software development supported by KEPs with the development achieved without it
Data-Aware Declarative Process Mining for Malware Detection
No full textMobile devices have become, in the last years, an essential tool used to perform daily activities. However, they also have become the target of continuous malware attacks usually coming out from new malware obtained as a variant of existing ones. For this reason, we suppose that by comparing the behavior of a new application with those of known malware applications it is possible to define it as malicious or trusted. According to this, the current study proposes an approach based on a data-aware declarative process mining technique to identify similarities and recurring patterns in the system call traces generated by a set of malicious mobile applications. The obtained characterization, represented by a set of declarative constraints within their data attributes, can be considered as a run-time fingerprint of a malware useful to evaluate the membership of a new application to a given malware family. The empirical validation of the proposed approach is performed on a dataset of more than 1200 trusted and malicious applications coming out from eight malware families and the obtained results show a very good discrimination ability
Empirical Validation on Knowledge Packaging supporting knowledge transfer
No full textTransfer of research results, as well as technological innovation, within an enterprise is a key success factor. The introduction of research results aims to improve efficacy and effectiveness of the production processes with respect to business goals, and also to better adapt the products to the market needs. Nevertheless, it is often difficult to transfer research results in production systems because it is necessary, among others, that knowledge be explicit and understandable by stakeholders. Such transfer is demanding, as so many researchers have been studying alternative ways to classic approaches such as books and papers that favour knowledge acquisition on behalf of users. In this context, we propose the concept of Knowledge Package (KP) with a specific structure as alternative. We have carried out an experiment which compared the efficacy of the proposed approach with the classic ones, along with the comprehensibility of the information enclosed in a KP rather than in a set of Papers. The experiment has pointed out that knowledge packages are more effective than traditional ones, for knowledge transfer
Empirical Investigation on Knowledge Packaging supporting Risk Management in Software Processes
No full textProject risks management is a non trivial task based on manager experience and knowledge collected in past executed projects. The larger the project manager experience and the available enterprise risk knowledge, the better the enterprise ability in risk management will be. For this reason the scientific community has focused its attention on the identification of methods, tools, and techniques for formalizing experience and know-how and making it available for other projects. In this sense, the authors have already presented a Risk Knowledge Package [1] for managing risk knowledge during software process execution. The work here proposed represents the continuation of such studies. In particular, an empirical investigation in industrial field has been carried out. Such investigation, based on legacy projects of EDS Italia Software SpA, aims at validating the effectiveness and the precision of the proposed approach. The results obtained encourage and stimulate further investigations in different software contexts
- …
