34/Analítica

¡Nueva característica
en Moodle 3.4!

Nota: Urgente de Traducir. ¡ Anímese a traducir esta muy importante página !.     ( y otras páginas muy importantes que urge traducir)

Vista general

Comenzando con la versión 3.4, el núcleo de Moodle ahora implementa analítica del aprendizaje transparente, de próxima-generación, de código abierto, usando backends de aprendizaje de máquina que van más allá de la analítica descriptiva simple, para proporcionar predictores de éxito del estudiante, y diagnóstico final y prescripcionees (recomendaciones) para estudiantes y profesores.

En Moodle 3.4, este sistema viene con dos modelos interconstruidos:

• Estudiantes en riesgo de abandonar
• Sin actividad de enseñanza

El sistema puede ser extendido fácilmente con nuevos modelos personalizados, basados en metas, indicadores y otros componentes reutilizables. Para más información, vea la documentación en idioma inglés para desarrolladores Analytics API.

Características destacadas

• Dos modelos de predicción interconstruídos: "Estudiantes en riesgo de abandonar cursos" y "Sin actividad de enseñanza".
• Un conjunto de indicadores de compromiso del estudiante basados en la Community of Inquiry.
• Herramientas interconstruídas para evaluar modelos contra sus datos del sitio
• Notificaciones proactivas para instructores usando Eventos
• Los instructores pueden enviar con facilidad mensajes a los estudiantes identificados por el modelo, o saltar al Reporte de perspectiva para ese estudiante para ver más detalles acerca de la actividad del eestudiante
• Una API para construir indicadores y modelos de predicción para plugins Moodle de terceros
• Tipo de plugin de backend para aprendizaje de máquina - soporta PHP y Python, y puede ser extendido para implementar otros backends de aprendizaje de máquina

Nota: PHP 7.x es requerido.

Limitaciones

This release of Moodle Learning Analytics has the following limitations:

• Models included in this release must be "trained" on a site with previous completed courses, ideally using the Moodle course completion feature. The current models cannot make predictions on a site until this is done.
• The prediction model included with this version requires that courses have fixed start and end dates, and is not designed to be used with rolling enrollment courses. Models that support a wider range of course types will be included in future versions of Moodle.
• Models and predictions are only visible to teachers and administrators at present.

We are continuing to enhance Moodle Learning Analytics, and expanded capabilities will be released going forward. To help contribute to our progress, please join the conversation at the Moodle Learning Analytics Community. In particular, we still need data sets from a wide variety of Moodle-using institutions in order to be able to ship a working prediction model that does not depend on local site data before it can be used.

Configuraciones

You can access Analytics settings from Site administration > Analytics > Analytics settings.

Procesador de predicciones

Predictions processor selection

Prediction processors are the machine learning backends that process the datasets generated from the calculated indicators and targets and return predictions. Moodle core includes 2 prediction processors:

• The PHP processor is the default. There are no other system requirements to use this processor.
• The Python one is more powerful and it generates graphs that explain the model performance. It requires setting up extra tools: Python itself (https://wiki.python.org/moin/BeginnersGuide/Download) and the moodlemlbackend python package.

   pip install moodlemlbackend

Métodos de división del tiempo

Time splitting methods allow insights generated from one course to be used on another course, even if the two courses are not exactly the same length.

Time splitting methods

Each time splitting method divides the course duration into segments. At the end of each defined segment, the predictions engine will run and generate insights. It is recommended that you only enable the time splitting methods you are interested in using; the evaluation process will iterate through all enabled time-spitting methods, so the more time-splitting methods enabled, the slower the evaluation process will be.

Directorio de salida de modelos

Models output directory

This setting allows you to define a directory where machine learning backends data is stored. Be sure this directory exists and is writable by the web server.

Gestión del modelo

Moodle can support multiple prediction models at once, even within the same course. This can be used for A/B testing to compare the performance and accuracy of multiple models.

Moodle core ships with two prediction models Estudiantes een riesgo de abandonar and Sin enseñanza. Additional prediction models can be created by using Analytics API. Each model is based on the prediction of a single, specific "target," or outcome (whether desirable or undesirable), based on a number of selected indicators.

You can manage your system models from Site Administration > Analytics > Analytics models.

These are some of the actions you can perform on a model:

• Get predictions: Train machine learning algorithms with the new data available on the system and get predictions for ongoing courses. Predictions are not limited to ongoing courses, this depends on the model.
• Evaluate: (disabled by default) Evaluate the prediction model by getting all the training data available on the site, calculating all the indicators and the target and passing the resulting dataset to machine learning backends, they will split the dataset into training data and testing data and calculate its accuracy. Note that the evaluation process use all information available on the site, even if it is very old, the accuracy returned by the evaluation process will generally be lower than the real model accuracy as indicators are more reliably calculated straight after training data is available because the site state changes along time. The metric used as accuracy is the Matthew’s correlation coefficient (good metric for binary classifications)
• Log: View previous evaluations log, including the model accuracy as well as other technical information generated by the machine learning backends like ROC curves, learning curves graphs, the tensorboard log dir or the model's Matthew’s correlation coefficient. The information available will depend on the machine learning backend in use.
• Edit: You can edit the models by modifying the list of indicators or the time-splitting method. All previous predictions will be deleted when a model is modified. Models based on assumptions (static models) can not be edited.
• Enable / Disable: The scheduled task that trains machine learning algorithms with the new data available on the system and gets predictions for ongoing courses skips disabled models. Previous predictions generated by disabled models are not available until the model is enabled again.
• Export: Export your site training data to share it with your partner institutions.
• Invalid site elements: Reports on what elements in your site can not be analysed by this model
• Clear predictions: Clears all the model predictions and training data

You can force the model evaluation process to run from the command line:

$ admin/tool/analytics/cli/evaluate_model.php 

Modelos del núcleo

Estudiantes en riesgo de abandonar

Este modelo predice estudiantes que están en riesgo de no-finalizar (abandonar / desertar) de un curso Moodle, basándose en un bajo compromiso del estudiante. En este modelo, la definición de "abandonar" es "sin actividad del estudiante en el último cuarto del curso." Este modelo de predicción usa el modelo de la Community of Inquiry de compromiso del estudiante, que consiste de tres partes:

• Presencia cognitiva
• Presencia social
• Presencia del profesor

This prediction model is able to analyze and draw conclusions from a wide variety of courses, and apply those conclusions to make predictions about new courses. The model is not limited to making predictions about student success only in exact duplicates of courses offered in the past. However, there are some limitations:

1. This prediction model assumes that courses have fixed start and end dates, and is not designed to be used with rolling enrollment courses. Models that support a wider range of course types will be included in future versions of Moodle. Because of this model design assumption, it is very important to properly set course start and end dates for each course to use this model. If both past courses and ongoing courses start and end dates are not properly set predictions cannot be accurate. Because the course end date field was only introduced in Moodle 3.2 and some courses may not have set a course start date in the past, we include a command line interface script:

$ admin/tool/analytics/cli/guess_course_start_and_end.php 

This script attempts to estimate past course start and end dates by looking at the student enrolments and students' activity logs. After running this script, please check that the estimated start and end dates script results are reasonably correct.

1. This model requires a certain amount of in-Moodle data with which to make predictions. At the present time, only core Moodle activities are included in the indicator set (see below). Courses which do not include several core Moodle activities per “time slice” will have poor predictive support in this model. This prediction model will be most effective with fully online or “hybrid” or “blended” courses with substantial online components.

Sin enseñanza

Las intuiciones de este modelo le informarán a los mánagers (gestores) del sitio sobre cursos con una fecha de inicio próxima que no tienen actividad de enseñanza. Este es un modelo simple y no usa el backend de aprendizaje de máquina para regresar predicciones. Basa las predicciones en asunciones; por ejemplo, no hay enseñanza si no hubiera estudiantes.

Predicciones e Intuiciones

Models will start generating predictions at different point in time, depending on the site prediction models and the site courses start and end dates.

Each model defines which predictions will generate insights and which predictions will be ignored. This is an example of Students at risk of dropping out prediction model; if a student is predicted as not at risk no insight is generated as what is interesting is to know which students are at risk of dropping out of courses, not which students are not at risk.