Este documento presenta una introducción a la analítica del aprendizaje. Explica cómo los datos generados por estudiantes pueden usarse para medir el progreso del aprendizaje, predecir la deserción y mejorar las estrategias educativas. También incluye ejemplos de cómo se han utilizado métodos estadísticos y de minería de datos para analizar videos, audios y datos de plumas digitales con el fin de comprender mejor el proceso de aprendizaje.
3. Grupo de Investigación en
Tecnologías para la Enseñanza y el Aprendizaje
• El material adecuado en el momento adecuado.
• Medir el proceso de aprendizaje.
• Muchos tutores por estudiante.
5. Los datos revelan:
• Nuestros sentimientos
• Nuestras actitudes
• Nuestas conexiones sociales
• Nuestras intenciones
• Lo que hicimos
• Lo que hacemos
• Lo que haremos
10. Sensemaking
“Sensemaking is a motivated, continuous effort
to understand connections . . . in order to
anticipate their trajectories and act effectively”
(Klein et al. 2006)
23. Que pasa en Educación
¿Cómo va tu curso?
¿Están tus estudiantes aprendiendo?
¿Funcionan tus estrategias?
¿Porqué los alumnos se retiran?
¿En que invertir los fondos?
¿Como van nuestros profesores?
¿Estoy estudiando suficiente?
¿Que hago para mejorar?
¿Donde estoy fallando?
24.
25.
26. Siemens, George, and Phil Long. "Penetrating the fog: Analytics in learning
and education." Educause Review 46.5 (2011): 30-32.
36. “Colleges Mine Data to
Predict Dropouts”
“At the University System of
Georgia, researchers monitored
how frequently students viewed
discussion posts and content pages
on course Web sites for three
different courses to find
connections between online
engagement and academic
success. In the graph below,
students who were "successful"
received an A, B, or C in the class,
and students who were
"unsuccessful" received a D, F,
or an incomplete.”
- 5/30/08 Chronicle of Higher Ed.
47. Cohere
• Annotations or
discussion as a
network of
rhetorical moves
• Users must reflect
on, and make
explicit, the nature
of their contribution
Simon Buckingham Shum, Anna De Liddo
54. GPA vs. Calificación en el Curso
Calificación > GPA
Calificación < GPA
0
Calificación = GPA
Tres escenarios:
Diferencias entre el
GPA y la calificación en el
curso
> 0< 0
57. Cursos Difíciles (Top 10)
Percibido Estimado
Algorithms Analysis
Operating Systems
Physics A
Differential Equations
Linear Algebra
Programming Fundamentals
Object-Oriented Programming
Differential Calculus
Data Structures
Statistics
Operating Systems
Statistics
Differential Equations
Linear Algebra
Programming Languages
Electrical Networks I
Artificial Intelligence
Programming Fundamentals
Data Structures
Hardware Architecture and Organization
60. CORE - CS CURRICULUM
Basic Physics
Integral Calculus
Multivariate Calculus
Electrical Networks
Digital Systems I
Hardware Architectures
Operative Systems
General Chemistry
Programming
Fundamentals
Object-oriented
Programming
Data Structures
Programming
Languages
Database Systems I
Software Engineering I
Software Engineering II
Oral and Written
Communication Techniques
Computing and Society
Discrete Mathematics
Algorithms Analysis
Human-computer
Interaction
Differential Calculus
Linear Algebra
Differential Equations
Ecology and
Environmental Education
Statistics
Economic Engineering I
Artificial Intelligence
PROFESSIONAL TRAINING HUMANITIES BASIC SCIENCE
63. Estructura Subyacente
Electrical
Networks
Differential
Equations
Software Engineering II
Software Engineering I
HCI
Oral and Written
Communication Techniques
General Chemistry
Programming
Languages
Object-Oriented
Programming
Data Structures
Artificial Intelligence
Operative Systems
Software Engineering
Object-Oriented Programming
Economic Engineering
Hardware Architectures
Database Systems
Digital Systems I
HCI
Differential and Integral Calculus
Linear Algebra
Multivariate Calculus
Digital Systems I
Basic Physics
Programming Fundamentals
Discrete Mathematics
General Chemistry
Statistics
Data Structures
Computing and Society
Algorithms Analysis
Differential Equations
Ecology and Environmental Education
Object-Oriented Programming
FACTOR 1: Ciencias Básicas
FACTOR 2: CS Avanzado
FACTOR 3:
Interacción con el
Cliente
FACTOR 4:
Programación
FACTOR 5: El factor ?
64. La agrupación no es como
esperábamos
¿Qué hacer con las materias que no se agrupan?
82. Video: Uso de la Calculadora
was
on
hat
ved
in-
and
ing
by
ent
was
core
ven
iffi-
on,
ex-
ath
t et
formations capabilities provided by OpenCV. While there
were some frames in which this matching was not possible
due to object occlusions or changes in the illumination of
the calculator, in general the described detection technique
was robust and provided useful position and direction data.
Figur e 1: D et er m inat ion of which st udent is using
83. Video: Distancia de la Cabeza al Centro
de la Mesa
lem
d to
cu-
par-
spe-
d as
pre-
ode-
ant
mall
ndi-
here
ned
de-
ary
ude,
re-
om
and then, the average of these distances is obtained by prob-
lem (see Figure 3). Additionally, the variance of the average
distance head to table (SD-DHT), was calculated to deter-
mine if a participant remains mostly static or varies his or
her distance to the table.
Figure 3: Calculat ion of t he dist ance of t he st udent ’s
86. Resultado
• Tres Caracteristicas:
– Escritor más rápido (Digital Pen)
– Porcentaje del Uso de la Calculadora (Video)
– Número de Veces en se mencionan Números
(Audio)
• Pueden predecir quien es el experto 80% del
tiempo
• Puden predecir quien resolverá el problema
correctamente 60% del tiempo
88. Analítica del Aprendizaje
• Ya está aquí y está teniendo resultados. ¿Ud.
la usa en su institución?
• No resuelve los problemas, solo inicia las
discusiones para resolverlos
• Necesita una nueva especie de profesional: El
científico de datos educativos
Key (to UMBC) is that CMS usage ALONE is established as an indicator of student success. To date, many academic analytics projects have focused on predictive data models that may have more to do with what students did or where they came from BEFORE stepping foot on campus.
Highly interactive online courses are predictive of student success, but variability among faculty course design means the LMS can never rise above “the course level” in terms of a “one size fits all” intervention solution.