Description
Every teacher knows, that interest, active participation and motivation are important factors in the learning process. However, Intelligent Tutoring Systems (ITS) and other e-learning environments almost always address only the cognitive goals. The AFFITS project addresses that challenge and aims at developing new methods and tools for recognition, representation and modelling of affect for ITS. Affect–awareness of ITS is defined in the project as the system being aware of the emotional state of a learner and being able to make intervention, when the learning process is endangered. The main research question to be answered by the project is: How to effectively monitor, represent and interpret affect in Intelligent Tutoring Systems to facilitate emotional states that support learning process? Detailed AFFITS objectives include design and verification of: - emotion recognition algorithms based on textual analysis and input device usage patterns, - trustworthiness model dealing with emotion uncertainty and fuzziness based on multimodality and theory of evidence and - affect-aware control mechanisms dedicated for ITS. The project aims not only at providing some new methods in affect recognition, interpretation and control but also combining them into one unified framework, providing that partial results work with each other to support affect-awareness in Intelligent Tutoring Systems. The AFFITS project aims at bringing some contribution to the methods of affect processing in ITS, but our dream is to reshape the way we interact with computers, especially providing a touch of humanity to sometimes too technical e-learning environments.
Summary of project results
The main research question of AFFITS project: „How to effectively monitor, represent and interpret affect in educational environments to facilitate emotional states that support learning process?" was addressed in multiple studies and experiments pushing forward the knowledge on recognizing and processing emotions in educational processes. The AFFITS project provided some new methods in affect recognition and interpretation, but also combined them into one unified framework, providing that partial results work with each other to support affect-awareness in educational systems. The proposed affect-awareness framework is not intended to be a complete affect-processing engine, but rather an extendable (modular and maintainable) structure to be applied in many domains and be modifiable with the progress ofthe affective learning domain, with new algorithms easily detached, exchanged or optimized. The main results of the project include: a definition of criteria for choosing emotion recognition channels for educational systems, including perceived disturbance, robustness, accuracy and compatibility; affective intervention design process (AFFINT) that combines analysis of the designed application with knowledge of affective phenomena and affective tools in order to formulate an affective intervention model for an application; design and implementation of new algorithms for affect recognition based on NLP and behavioral data; development of Polish lexicon of affect-annotated words (SentiD); trustworthiness model, that deals with uncertainty of emotion recognition and factors, that influence the fuzziness and confidence in recognition result; scoreboard design pattern. The project results and especially investigation of uncertainty in emotion recognition performed within AFFITS project might have a significant impact both on research and society. Project results were disseminated in the form of publications: 1 publication in international (IF) journal, 1 publication in national journal, 1 book chapter, 8 papers published in conference proceedings, 3 reports with 4 more publications submitted and further 4 planned. Project was also promoted at ten national and international conferences. The AFFITS project has a significant impact on Principal lnvestigator and other researchers work, including female researchers in the following ways: increased publishing output, increased dissemination and recognition of research, project management and cooperation skills.
Summary of bilateral results