Search

Learning Analytics focuses on measuring and analyzing learners’ data, such as formative assessment of collaborative writing and individual students’ performance. This work applied machine learning approaches and natural language processing to assess university students’ reports in the knowledge building domain. Students (n = 32) wrote essays about knowledge building topics, and the professor used Dublin descriptors as assessment criteria to evaluate the students’ reports. This paper presents the results of a study on validating whether students’ reports are aligned with Dublin descriptors for qualifications awarded. We have used two classification models: Support Vector Machine (SVM) and Random Forest Classifier (RFC), to predict manual annotations from experts in students’ reports. Random Forest Classifier reached 73% accuracy. We concluded that machine learning algorithms and natural language processing (NLP) together are useful for automating the classification of the students’ reports using manual annotations.

The rise of Open Educational Resources (OER) in education has allowed the issue of the quality of these resources to be increasingly relevant. The OER can be defined as resources and pedagogical materials that reside in the public domain and that allow third parties to use them freely; and under this strategy, open educational resources progressively integrates educational practices from formal, informal and lifelong learning. The purpose of this paper is to present a framework to evaluate the quality of OER in order to promote the discovering and reusability of resources by users. The framework designed is based on three tiers. The first tier is a development quality model based on the analysis of different quality proposals existing in the areas of e-learning, learning objects and open educational resources, by this model gets a quality value of a resource. The second tier consists of implementing Semantic Web technologies and knowledge representation, natural language processing techniques, and data interoperability by semi-automatic processes. And finally, The third tier gets maturity levels using quality values got the first tier both in the initial state of the OER and after its enrichment. In summary, the proposal presents a theoretical background to OER quality evaluation by an improvement to the existing quality framework that integrates developing technologies and techniques that allow the assessment of open educational resources.

The bibliographic databases have abstract and citations of scientific articles, the summary being the most consulted section of an article. In order to classify and address the entries in a system of indexing and retrieval of information in the databases of a manuscript, there are keywords, which in many cases this information should not achieve greater dissemination. This paper presents an evaluation of the semantic relatedness between the abstract of scientific papers and their keywords. This analysis will be using word2vec that is a predictive model, and it will find the nearest words. Thus, this study is focused on the metadata quality assessment through the similar semantics between two words that allow the accuracy in relation to metadata of scientific databases.

Open Education is a movement that was born with the purpose of bringing knowledge to disadvantaged sectors and opening the doors to better education opportunities for all. Open Educational Resources (OER) such as Open CourseWare (OCW) has become support resources in the educational environment. For this reason, the quality of the repositories is highlighted by the quality of their metadata. The metadata is one characteristic of the repositories, that facilitates the search and discovery tasks of educational resources, in this way ensures their reuse. Consequently, to assure universal access to quality knowledge there are some metrics of metadata quality to evaluate OCW repository metadata: completeness, consistency, coherence, accuracy, provenance, and accessibility. In this study, accuracy and provenance are prioritized as quality metrics for metadata quality evaluation because they support potential users in the search and selection of OCW resources. This paper uses a set of data from the repository of semantic search engine Serendipity in order to evaluate the selected quality metadata metrics, applying cosine distance technique and calculation of completeness of provenance metadata because it is an important aspect of validating quality criteria for ICT tools. When the corresponding values of the study metrics are obtained, the analysis of the obtained results is performed. Two important findings are identified. First, the cosine technique is an important tool to find the semantic distance between the resource and its metadata. Second, the PAV ontology provides provenance properties of an OCW that helps in obtaining the provenance quality of a resource. This paper is limited to the dataset available in Serendipity semantic search engine, however, it is considered that the interpretation of the findings does not vary if we use a specific repository.

The present work uses Hadoop as the core processing in the Big Data environment. There are several open sources tools from the Hadoop ecosystem that facilitate the processing of enormous volumes of data. In this paper, we have worked with Apache Flume and Apache Hive tools for the study case of the 2017 presidential elections in Ecuador. The analysis of data generated from Twitter social network focuses mainly in the first round of balloting of Ecuador’s 2017 presidential election. These generated data have been obtained, stored, processed and analyzed to comply with the characteristics of the information that is considered Big Data. The selected tools have been evaluated in their architecture, installation, and use. Finally, the data have been evaluated under certain quality criteria or dimensions.

Promoting accessibility allows that everyone can access a service, regardless of their cognitive, physical or technical abilities. Then, it is important to make a site accessible for everyone, especially the public and private intuitions should consider the accessibility web. This work presents a web accessibility diagnosis of some subdomains of university web portal and correction the errors found as absence of compliance properties with the web accessibility guides to reach the level of compliance AA normalized by WCAG. The analysis was done in 2016. The evaluation was based on the Web Content Accessibility Guidelines (WCAG) version 2.0, which identifies opportunities for improvement in order to provide an accessible web portal. This study identifies the problems that must be solved in order to make web content more accessible to people with disabilities.

The present work presents an analysis to terms related to Big Data, Hadoop and presents results by means of RHadoop the combination of two technologies as are R and Hadhoop, these technologies are complemented in an advantageous way, because it allows the analysis and visualization of large volumes Of data, in addition a case study of the tweet is generated that generates from a user account using Hadoop (Apache Hive) and the presentation of reports with RHadoop that support to the Managers of the organizations to a better decision-making. In order to do this, a detailed search has been made regarding Big Data, Hadoop Framework and the means of visualization and generation of a Data Volume with RHadoop, in which a synthesis of the different important terms was made, Arriving to determine different areas of application, in addition is presented a case study of a data volume with Hadoop applied to tweets generated from the social network Twitter. In this context it is concluded that with the help of the Hadoop Framework we can process a large volume of data, since its architecture has the Hadoop Distributed File System that provides a high performance of access to data of the application and Apache Hive that executes the processes In parallel with the integration of tools such as RHadoop allows the analysis of a large amount of information and submit reports that support the decision-making of organizations.

This paper presents an analysis and application of the Web 2.0 tools, the objective of this research work is that students of Computer who are in the first cycle of different degrees onsite | earning of Universidad Tecnica Particular de Loja(UTPL) organize searching and communicate the information as support for the improvement of the teaching-learning competences of UTPL educational model. For that a search of information and management of the tools Web 2.0 was done. which are published by the students using an Educational Blog as well as the use and revision of Web 3.0 tools to compare the support provided in the Education, Technology, Knowledge, Social and Learning area. To conclude this paper identifies the interest of students who are not related to Systems Engineering, in the proper use of Web 2.0 and Web 3.0 tools. strengthening the learning habit and raising the digital competences according to UTPL educational model.

El uso de la tecnología provoca cambios sociales. Esto incluye el trabajo en el ámbito universitario en donde está cambiando tanto la forma de ejercer la docencia como la forma de aprender y se requiere conocer el efecto del uso de la tecnología sobre el rendimiento del alumnado. En este trabajo se investigó la incidencia del uso de Internet sobre el éxito académico del alumnado de cinco universidades de Ecuador. Se levantó una muestra aleatoria de 4.697 personas y se las categorizó en perfiles de uso de Internet para actividades académicas y para entretenimiento, utilizando análisis factorial y análisis clúster. Las categorías resultantes se utilizaron como variables independientes en modelos de regresión logística multinomial que buscaban determinar si el uso de Internet tenía incidencia sobre el éxito académico. Los resultados muestran que quienes realizan actividades interactivas con pares y profesores o quienes utilizan de forma balanceada las distintas herramientas de Internet tienden a un mayor éxito académico que aquellos que solo buscan información. En lo referente al entretenimiento, se encontró una incidencia positiva del uso de Internet sobre el éxito académico. Los estudiantes que realizan descargas de contenido de audio, video y software, y quienes utilizan todas las posibilidades de entretenimiento, presentan menor tendencia a suspender que los estudiantes que utilizan mínimamente Internet. En cuanto al género se presentan diferencias en los usos académicos y de entretenimiento, The use of technology is changing the way things are done, including the work in universities where the teaching and learning process are changing, and it is required to know the effect of technology on student achievement. In this research work, we present the influence of Internet use on academic success of students from five universities in Ecuador. A random sample of 4,697 people was got up and categorized in two groups: the use of Internet in academic activities and entertainment, using factor analysis and cluster analysis; the resulting categories were used as independent variables in multinomial logistic regression model which are seeking to determine if the use of Internet has impacted on academic success. The results show that people who perform interactive activities with peers and teachers or use in a balanced way the different internet tools tend to have more academic success than those who only seeks information. Regarding to the use of Internet in entertainment, a positive impact was found on academic achievement. Students who download audio, video and software, and students who use all the entertainment possibilities show less likely to fail than who using minimally Internet. In terms of gender, it has different effects for entertainment and academic purposes