Affective Computing for detecting psychological Flow state: a definition and methodological problem

Read the Paper (or contact me at elena.sajno-at-phd.unipi.it)

Reference:

Sajno, E. (2023, September). Affective Computing for detecting psychological Flow state: a definition and methodological problem. In 2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) (pp. 1-5). IEEE.

Flow is a mental state connected to optimal experiences and high performance. Existing detection systems are limited to post-hoc or require repeated and distracting assessments. Affective Computing offers the potential to be a viable framework for its detection and characterization. The formalization of such a model depends, however, on reliable assessment, elicitation, and detection of Flow. To this end, this work proposes that 1) Flow can be charted as a high valence, high arousal, and high dominance state: concordance of results with traditional evaluation scales (e.g., Flow State Scale) would be checked to confirm the validity of the assessment methods. 2) A video game, with difficulties tailored to the subject’s performance, can elicit Flow, as well as Engagement, boredom, or anxiety. 3) Specific physiological correlates (i.e., ECG and EDA) can be leveraged for its detection.

Follow the Flow: A Prospective on the On-Line Detection of Flow Mental State through Machine Learning

Read the Paper (or contact me at elena.sajno-at-phd.unipi.it)

Reference:

Sajno, E., Beretta, A., Novielli, N., & Riva, G. (2022, October). Follow the Flow: A Prospective on the On-Line Detection of Flow Mental State through Machine Learning. In 2022 IEEE International Conference on Metrology for Extended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) (pp. 217-222). IEEE. 

Flow is a precious mental status for achieving high sports performance. It is defined as an emotional state with high valence and high arousal levels. However, a viable detection system that could provide information about it in real-time is not yet recognized. The prospective work presented here aims to the creation of an online flow detection framework. A supervised machine learning model will be trained to predict valence and arousal levels, both on already existing databases and freshly collected physiological data. As final result, the definition of the minimally expensive (both in terms of sensors and time) amount of data needed to predict a flow status will enable the creation of a real-time detection interface of flow.

A Feasibility Study on Improving Emotion Recognition from ECG Signals and HRV Features Through Baseline Clusterization

Read the Paper (or contact me at elena.sajno-at-phd.unipi.it)

Reference:

Sajno, E., & Riva, G. (2022). Follow the Flow: Artificial Intelligence and Machine Learning for Achieving Optimal Performance. Cyberpsychology, behavior and social networking, 25(7), 476-477