Persona:
Cabestrero Alonso, Raúl

Foto de perfil
Dirección de correo electrónico
ORCID
0000-0003-3697-1303
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Cabestrero Alonso
Nombre de pila
Raúl
Nombre

Filtros

2012 - 20132
Restablecer filtros

Ajustes

Nivel de acceso: info:eu-repo/semantics/openAccess × search.filters.applied.f.itemDepartamento: Inteligencia Artificial ×

Resultados de la búsqueda

Mostrando 1 - 2 de 2
  • Miniatura
    Publicación
    Challenges for Inclusive Affective Detection in Educational Scenarios
    (Springer Nature, 2013) Santos, Olga C.; Rodríguez Ascaso, Alejandro; González Boticario, Jesús; Salmeron Majadas, Sergio; Quirós Expósito, Pilar; Cabestrero Alonso, Raúl
    There exist diverse challenges for inclusive emotions detection in educational scenarios. In order to gain some insight about the difficulties and limitations of them, we have analyzed requirements, accommodations and tasks that need to be adapted for an experiment where people with different functional profiles have taken part. Adaptations took into consideration logistics, tasks involved and user interaction techniques. The main aim was to verify to what extent the same approach, measurements and technological infrastructure already used in previous experiments were adequate for inducing emotions elicited from the execution of the experiment tasks. In the paper, we discuss the experiment arrangements needed to cope with people with different functional profiles, which include adaptations on the analysis and results. Such analysis was validated in a pilot experiment with 3 visually impaired participants.
  • Miniatura
    Publicación
    MAMIPEC - Affective modeling in inclusive personalized educational scenarios
    (IEEE Technical Committee on Learning Technology,, 2012) Santos, Olga C.; González Boticario, Jesús; Arevalillo Herráez, Miguel; Saneiro Silva, María del Mar; Cabestrero Alonso, Raúl; Campo Adrián, María del Campo; Manjarrés Riesco, Ángeles; Moreno Clarí, Paloma; Quirós Expósito, Pilar; Salmeron Majadas, Sergio
    There is agreement in the literature that affect influences learning. In turn, addressing affective issues in the recommendation process has shown their ability to increase the performance of recommender systems in non-educational scenarios. In our work, we combine both research lines and describe the SAERS approach to model affective educational recommendations. This affective recommendation model has been initially validated with the application of the TORMES methodology to specific educational settings. We report 29 recommendations elicited in 12 scenarios by applying this methodology. Moreover, a UML formalized version of the recommendations model which can describe the recommendations elicited is presented in the paper.