scholarly journals Machine Learning im Bildungskontext: Evidenz für die Genauigkeit der automatisierten Beurteilung von Essays im Fach Englisch

2020 ◽  
pp. 1-12
Author(s):  
Jennifer Meyer ◽  
Thorben Jansen ◽  
Johanna Fleckenstein ◽  
Stefan Keller ◽  
Olaf Köller
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Open Source Software ◽  
Text Analysis ◽  
Gradient Boosting ◽  
Testing Service ◽  
The Common ◽  
Educational Testing Service ◽  
Lineare Regression ◽  
Analysis Platform

Zusammenfassung. Argumentatives Schreiben ist eine bedeutsame Kompetenz in der Fremdsprache Englisch. Entsprechende Schreibaufgaben sind Teil von Schulabschlussprüfungen in der Sekundarstufe II und von Zugangstests für Hochschulen (z.B. TOEFL®). Trotz ihrer Bedeutsamkeit wurden diese komplexen Schreibleistungen bisher im Kontext großer Schulleistungsuntersuchungen kaum empirisch untersucht. Ein Grund dafür ist die aufwendige Auswertung der Essays, für die eine große Anzahl speziell trainierter Kodiererinnen und Kodierer zur Beurteilung benötigt wird. Um den Aufwand der Auswertung zu reduzieren, können Machine Learning Verfahren eingesetzt werden, welche die Urteile der Kodiererinnen und Kodierer approximieren. Dabei werden linguistische Eigenschaften der Essays automatisiert erfasst, die dann genutzt werden, um mit Hilfe von statistischen Verfahren des maschinellen Lernens die menschlichen Urteile vorherzusagen. In der vorliegenden Arbeit soll dieses Vorgehen dargestellt und das Potenzial solcher automatisierten Prozeduren in Bezug auf die Vorhersagegenauigkeit untersucht werden. Dazu lagen Texte von N = 2179 Schülerinnen und Schülern der 11. Jahrgangsstufe in Deutschland und der Schweiz vor. Zur Kodierung der Texte wurde die open source-Software The Common Text Analysis Platform (CTAP) eingesetzt, die linguistische Textmerkmale automatisch kodiert. Auf Basis dieser Textmerkmale wurden die vorliegenden Urteile von trainierten Kodiererinnen und Kodierern des Educational Testing Service (ETS) vorhersagt. Die Genauigkeit der Vorhersage erwies sich als zufriedenstellend ( r = .75; Anteil genauer Übereinstimmung: 42%) und konnte im Vergleich mit einer etablierten kommerziellen Software des ETS (e-rater®; r = .81; Anteil genauer Übereinstimmung: 42%) bestehen. Es wurden vergleichbare Ergebnisse für die lineare Regression sowie Gradient Boosting als Analysestrategien zur Vorhersage der menschlichen Urteile gefunden. Möglichkeiten und Limitationen der automatisierten Textbeurteilung und deren Anwendung in Forschung und Praxis werden diskutiert.

Prospects of Open Source Software for Maximizing the User Expectations in Heterogeneous Network

2021 ◽  
pp. 257-271
Author(s):  
Pushpa Singh ◽  
Rajeev Agrawal
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Real Time ◽  
Open Source Software ◽  
Heterogeneous Networks ◽  
Heterogeneous Network ◽  
Research Work ◽  
Software Tool ◽  
Knn Classifier ◽  
User Expectations

This article focuses on the prospects of open source software and tools for maximizing the user expectations in heterogeneous networks. The open source software Python is used as a software tool in this research work for implementing machine learning technique for the categorization of the types of user in a heterogeneous network (HN). The KNN classifier available in Python defines the type of user category in real time to predict the available users in a particular category for maximizing profit for a business organization.

PREDICTING SOFTWARE CHANGE IN AN OPEN SOURCE SOFTWARE USING MACHINE LEARNING ALGORITHMS

2013 ◽  
Vol 20 (06) ◽  
pp. 1350025
Author(s):  
RUCHIKA MALHOTRA ◽  
ANKITA JAIN BANSAL
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Open Source Software ◽  
Roc Analysis ◽  
Area Under The Curve ◽  
Machine Learning Algorithms ◽  
Operating Characteristics ◽  
Preventive Actions ◽  
Change Proneness ◽  
The Relationship

Due to various reasons such as ever increasing demands of the customer or change in the environment or detection of a bug, changes are incorporated in a software. This results in multiple versions or evolving nature of a software. Identification of parts of a software that are more prone to changes than others is one of the important activities. Identifying change prone classes will help developers to take focused and timely preventive actions on the classes of the software with similar characteristics in the future releases. In this paper, we have studied the relationship between various object oriented (OO) metrics and change proneness. We collected a set of OO metrics and change data of each class that appeared in two versions of an open source dataset, 'Java TreeView', i.e., version 1.1.6 and version 1.0.3. Besides this, we have also predicted various models that can be used to identify change prone classes, using machine learning and statistical techniques and then compared their performance. The results are analyzed using Area Under the Curve (AUC) obtained from Receiver Operating Characteristics (ROC) analysis. The results show that the models predicted using both machine learning and statistical methods demonstrate good performance in terms of predicting change prone classes. Based on the results, it is reasonable to claim that quality models have a significant relevance with OO metrics and hence can be used by researchers for early prediction of change prone classes.

scholarly journals The case for free and open source software in research and scholarship

2021 ◽  
Vol 379 (2197) ◽  
Author(s):  
Laura Fortunato ◽  
Mark Galassi
Keyword(s):  
Open Source ◽  
Open Source Software ◽  
Research Process ◽  
Open Science ◽  
Support Staff ◽  
Research Quality ◽  
Open Research ◽  
The Common

Free and open source software (FOSS) is any computer program released under a licence that grants users rights to run the program for any purpose, to study it, to modify it, and to redistribute it in original or modified form. Our aim is to explore the intersection between FOSS and computational reproducibility. We begin by situating FOSS in relation to other ‘open’ initiatives, and specifically open science, open research, and open scholarship. In this context, we argue that anyone who actively contributes to the research process today is a computational researcher, in that they use computers to manage and store information. We then provide a primer to FOSS suitable for anyone concerned with research quality and sustainability—including researchers in any field, as well as support staff, administrators, publishers, funders, and so on. Next, we illustrate how the notions introduced in the primer apply to resources for scientific computing, with reference to the GNU Scientific Library as a case study. We conclude by discussing why the common interpretation of ‘open source’ as ‘open code’ is misplaced, and we use this example to articulate the role of FOSS in research and scholarship today. This article is part of the theme issue ‘Reliability and reproducibility in computational science: implementing verification, validation and uncertainty quantification in silico ’.

scholarly journals Applying Machine Learning Techniques to Predict the Maintainability of Open Source Software

2019 ◽  
Vol 8 (5S3) ◽  
pp. 192-195
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Open Source Software ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Software Applications ◽  
Learning Techniques ◽  
Software Maintainability ◽  
Quality Aspect

Software maintainability is a vital quality aspect as per ISO standards. This has been a concern since decades and even today, it is of top priority. At present, majority of the software applications, particularly open source software are being developed using Object-Oriented methodologies. Researchers in the earlier past have used statistical techniques on metric data extracted from software to evaluate maintainability. Recently, machine learning models and algorithms are also being used in a majority of research works to predict maintainability. In this research, we performed an empirical case study on an open source software jfreechart by applying machine learning algorithms. The objective was to study the relationships between certain metrics and maintainability.

scholarly journals Development of framework for detecting smoking scene in video clips

2019 ◽  
Vol 13 (1) ◽  
pp. 22
Author(s):  
Poonam Ghuli ◽  
Shashank B N ◽  
Athri G Rao
Keyword(s):  
Machine Learning ◽  
Object Detection ◽  
Open Source ◽  
Image Recognition ◽  
Open Source Software ◽  
Software Library ◽  
Accurate Model ◽  
Video Clips ◽  
Warning Messages ◽  
Warning Message

<p>According to Global Adult Tobacco Survey 2016-17, 61.9% of people quitting tobacco the reason was the warnings displayed on the product covers. The focus of this paper is to automatically display warning messages in video clips. This paper explains the development of a system to automatically detect the smoking scenes using image recognition approach in video clips and then add the warning message to the viewer.  The approach aims to detect the cigarette object using Tensorflow’s object detection API. Tensorflow is an open source software library for machine learning provided by Google which is broadly used in the field image recognition. At present, Faster R-CNN with Inception ResNet is theTensorflow’s slowest but most accurate model. Faster R-CNN with Inception Resnet v2 model is used to detect smoking scenes by training the model with cigarette as an object.</p><p><em><br /></em></p>

scholarly journals Predicting CoVID-19 community mortality risk using machine learning and development of an online prognostic tool

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e10083 ◽  
Author(s):  
Ashis Kumar Das ◽  
Shiba Mishra ◽  
Saji Saraswathy Gopalan
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Open Source ◽  
Mortality Risk ◽  
Machine Learning Algorithms ◽  
Brier Score ◽  
Gradient Boosting ◽  
Support Vector ◽  
Prediction Tool ◽  
Online Prediction

Background The recent pandemic of CoVID-19 has emerged as a threat to global health security. There are very few prognostic models on CoVID-19 using machine learning. Objectives To predict mortality among confirmed CoVID-19 patients in South Korea using machine learning and deploy the best performing algorithm as an open-source online prediction tool for decision-making. Materials and Methods Mortality for confirmed CoVID-19 patients (n = 3,524) between January 20, 2020 and May 30, 2020 was predicted using five machine learning algorithms (logistic regression, support vector machine, K nearest neighbor, random forest and gradient boosting). The performance of the algorithms was compared, and the best performing algorithm was deployed as an online prediction tool. Results The logistic regression algorithm was the best performer in terms of discrimination (area under ROC curve = 0.830), calibration (Matthews Correlation Coefficient = 0.433; Brier Score = 0.036) and. The best performing algorithm (logistic regression) was deployed as the online CoVID-19 Community Mortality Risk Prediction tool named CoCoMoRP (https://ashis-das.shinyapps.io/CoCoMoRP/). Conclusions We describe the development and deployment of an open-source machine learning tool to predict mortality risk among CoVID-19 confirmed patients using publicly available surveillance data. This tool can be utilized by potential stakeholders such as health providers and policymakers to triage patients at the community level in addition to other approaches.

Overview of Multi-Factor Prediction Using Deep Neural Networks, Machine Learning, and Their Open-Source Software

2022 ◽  
pp. 1-28
Author(s):  
Richard S. Segall
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Open Source ◽  
Open Source Software ◽  
Limited Time ◽  
Software Company ◽  
Data Capacity ◽  
Network Software

This chapter first provides an overview with examples of what neural networks (NN), machine learning (ML), and artificial intelligence (AI) are and their applications in biomedical and business situations. The characteristics of 29 types of neural networks are provided including their distinctive graphical illustrations. A survey of current open-source software (OSS) for neural networks, neural network software available for free trail download for limited time use, and open-source software (OSS) for machine learning (ML) are provided. Characteristics of artificial intelligence (AI) technologies for machine learning available as open source are discussed. Illustrations of applications of neural networks, machine learning, and artificial intelligence are presented as used in the daily operations of a large internationally-based software company for optimal configuration of their Helix Data Capacity system.

Sign in / Sign up

Export Citation Format

Share Document