polito.it
Politecnico di Torino (logo)

Emotion Recognition Application on Desktop Application

Victor Pierre Virgile Seguin

Emotion Recognition Application on Desktop Application.

Rel. Gabriella Olmo. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2022

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (16MB) | Preview
[img] Archive (ZIP) (Documenti_allegati) - Altro
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (3MB)
Abstract:

??Traditional marketing research seeks to consciously comprehend the decision-making process of the consumer, whereas neuromarketing focuses at understanding customer conduct. The difficulty with conventional marketing research depends primarily on what the customer feels and believes. Our worldly perspective is generally guided by our emotions that are often changing. This is the reason why the project team aims to record the participant’s unconscious behaviour as well as his conscious behaviour. ??In this context, a desktop application was developed and its goal is to try and detect a participant’s emotion when faced to various types of Human Computer Interactions : a static image advertisement, a video advertisement and a website-based advertisement. ??The use of various physiological indicators called biomarkers in these three experiments is going to help the team get a better understanding of the participant’s emotions during the different experiments. Three different types of biomarkers were particularly studied for this project : eye tracking, face emotion recognition and galvanic skin resistance. ??A dedicated desktop application was created in order to manage the pathway of all described experiments, to record the participant’s behaviour and the participant’s biomarkers in the meantime. ??After that, a postprocessing software has been created with the aim of obtaining a starting point of analysis for the eye tracking data analysis, which I was the most involved in. It was used specifically for the website experiment’s scrolling and to compare two different versions of the same website. ??Finally, the statistical analysis of eye tracking data and face emotion recognition are detailed, with a possible example of how it is possible to detect emotions based on the participant’s arousal and valence using a multiple biomarker approach like in this specific project.

Relatori: Gabriella Olmo
Anno accademico: 2021/22
Tipo di pubblicazione: Elettronica
Numero di pagine: 71
Soggetti:
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-32 - INGEGNERIA INFORMATICA
Aziende collaboratrici: NON SPECIFICATO
URI: http://webthesis.biblio.polito.it/id/eprint/22726
Modifica (riservato agli operatori) Modifica (riservato agli operatori)