Person: Santos, Olga C.
Loading...
Email Address
ORCID
0000-0002-9281-4209
Birth Date
4 results
Search Results
Now showing 1 - 4 of 4
Publication Some insights into the impact of affective information when delivering feedback to students(Taylor and Francis Group, 2018-07-26) Cabestrero Alonso, Raúl; Quirós Expósito, Pilar; Santos, Olga C.; Salmeron Majadas, Sergio; Uria Rivas, Raul; González Boticario, Jesús; Arnau, David; Arevalillo Herráez, Miguel; Ferri, Francesc J.The relation between affect-driven feedback and engagement on a given task has been largely investigated. This relation can be used to make personalised instructional decisions and/or modify the affect content within the feedback. However, although it is generally assumed that providing encouraging feedback to students should help them adopt a state of flow, there are instances where those messages might result counterproductive. In this paper, we present a case study with 48 secondary school students using an Intelligent Tutoring System for arithmetical word problem solving. This system, which makes some common assumptions on how to relate affective state with performance, takes into account subjective (user's affective state) and objective information (previous problem performance) to decide the upcoming difficulty levels and the type of affective feedback to be delivered. Surprisingly, results revealed that feedback was more effective when no emotional content was included, and lead to the conclusion that purely instructional and concise help messages are more important than the emotional reinforcement contained therein. This finding shows that this is still an open issue. Different settings present different constraints generating related compounding factors that affect obtained results. This research confirms that new approaches are required to determine when, how and where affect-driven feedback is needed. Affect-driven feedback, engagement and their mutual relation have been largely investigated. Student's interactions combined with their emotional state can be used to make personalised instructional decisions and/or modify the affect content within the feedback, aiming to entice engagement on the task. However, although it is generally assumed that providing encouraging feedback to the students should help them adopt a state of flow, there are instances where those encouraging messages might result counterproductive. In this paper, we analyze these issues in terms of a case study with 48 secondary school students using an Intelligent Tutoring System for arithmetical word problem solving. This system, which makes some common assumptions on how to relate affective state with performance, takes into account subjective (user's affective state) and objective (previous problem performance) information to decide the difficulty level of the next exercise and the type of affective feedback to be delivered. Surprisingly, findings revealed that feedback was more effective when no emotional content was included in the messages, and lead to the conclusion that purely instructional and concise help messages are more important than the emotional reinforcement contained therein. This finding, which coincides with related work, shows that this is still an open issue. Different settings present different constraints and there are related compounding factors that affect obtained results, such as the message's contents and their target, how to measure the effect of the message on engagement through affective variables considering other issues involved, and to what extent engagement can be manipulated solely in terms of affective feedback. The contribution here is that this research confirms that new approaches are needed to determine when, how and where affect-driven feedback is needed. In particular, based on our previous experience in developing educational recommender systems, we suggest the combination of user-centred design methodologies with data mining methods to yield a more effective feedback.Publication A Machine Learning Approach to Leverage Individual Keyboard and Mouse Interaction Behavior From Multiple Users in Real-World Learning Scenarios(Browse Journals & Magazines, 2018) Salmeron Majadas, Sergio; Baker, Ryan S.; Santos, Olga C.; González Boticario, Jesús; https://orcid.org/0000-0002-0544-0887; https://orcid.org/0000-0002-3051-3232; https://orcid.org/0000-0002-9281-4209There is strong evidence that emotions influence the learning process. For this reason, we explore the relevance of individual and general mouse and keyboard interaction patterns in real-world settings while learners perform free text tasks. To this end, we have modeled users' mouse movements and keystroke dynamics with data mining techniques, building on previous related research and extending it in terms of some critical modeling issues that may have an impact on detection results. Inspired by practice in affective computing where physiological sensors are used, we argue for the creation of an interaction baseline model, as a reference point in the way how learners interact with the keyboard and mouse. To make the proposed affective model feasible, we have adopted a simplified 2-D self-labeling approach for labeling the users' affective state. Our approach to affect detection improves results when there is a small amount of data instances available and does not require additional affect-oriented tasks from the learners. Specifically, learners are only asked to self-reflect their emotional state after finishing the tasks and immediately selecting two values in the affect scale. The approach we have followed aims to distill two types of interaction patterns: 1) within-subject patterns (from a single participant) and 2) between-subject patterns (across all participants). Doing this, we aim to combine both the approaches as modeling factors, thus taking advantage of individual and general interaction patterns to predict affect.Publication Impact of Physiological Signals Acquisition in the Emotional Support Provided in Learning Scenarios(MDPI, 2019-10-17) Uria Rivas, R.; Rodriguez Sanchez, Cristina; Santos, Olga C.; Vaquero, Joaquin; Jesus G. Boticario; González Boticario, Jesús; https://orcid.org/0000-0001-9243-2166; https://orcid.org/0000-0002-9281-4209; https://orcid.org/0000-0002-6976-0564Physiological sensors can be used to detect changes in the emotional state of users with affective computing. This has lately been applied in the educational domain, aimed to better support learners during the learning process. For this purpose, we have developed the AICARP (Ambient Intelligence Context-aware Affective Recommender Platform) infrastructure, which detects changes in the emotional state of the user and provides personalized multisensorial support to help manage the emotional state by taking advantage of ambient intelligence features. We have developed a third version of this infrastructure, AICARP.V3, which addresses several problems detected in the data acquisition stage of the second version, (i.e., intrusion of the pulse sensor, poor resolution and low signal to noise ratio in the galvanic skin response sensor and slow response time of the temperature sensor) and extends the capabilities to integrate new actuators. This improved incorporates a new acquisition platform (shield) called PhyAS (Physiological Acquisition Shield), which reduces the number of control units to only one, and supports both gathering physiological signals with better precision and delivering multisensory feedback with more flexibility, by means of new actuators that can be added/discarded on top of just that single shield. The improvements in the quality of the acquired signals allow better recognition of the emotional states. Thereof, AICARP.V3 gives a more accurate personalized emotional support to the user, based on a rule-based approach that triggers multisensorial feedback, if necessary. This represents progress in solving an open problem: develop systems that perform as effectively as a human expert in a complex task such as the recognition of emotional statesPublication Exploring cognitive models to augment explainability in Deep Knowledge Tracing(ACM Digital Library, 2023-06-13) Labra, Concha; Santos, Olga C.; https://orcid.org/0009-0004-3499-6106; https://orcid.org/0000-0002-9281-4209Adaptive learning systems allow a personalized adaptation based on the characteristics of the student. Tracing the progress of knowledge and skills during the learning process through cognitive models is essential so that these systems can make appropriate decisions when carrying out personalization. This is the objective of Knowledge Tracing, which studies how to infer a cognitive model from the answers given to a sequence of questions or exercises. The incorporation of Deep Learning techniques in this field has given rise to Deep Knowledge Tracing (DKT) which usually has excellent predictive outcomes. The problem is that this increase in accuracy comes with a lack of explainability since Deep Learning models can be considered black boxes from which it is difficult to build interpretations or explanations. By contrast, traditional Knowledge Tracing methods are based on underlying learning models and provide a solid basis for explainability. In this paper we describe an ongoing research to build DKT models with a good trade-off between accuracy and explainability. To this end, we propose to use a loss function based on a mixup approach where the ground truth is a mix between the dataset labels and the predictions of a surrogate explainable model. The approach has potential to improve, not only explainability through the use of the surrogate, but also accuracy thanks to regularization effects. We will validate the approach by exploring, for different cognitive models, the trade-off curve that is obtained by plotting accuracy against explainability for different mixup values.