Automatic Emotion Recognition in Children with Autism: A Systematic Literature Review

Abstract

The automatic emotion recognition domain brings new methods and technologies that might be used to enhance therapy of children with autism. The paper aims at the exploration of methods and tools used to recognize emotions in children. It presents a literature review study that was performed using a systematic approach and PRISMA methodology for reporting quantitative and qualitative results. Diverse observation channels and modalities are used in the analyzed studies, including facial expressions, prosody of speech, and physiological signals. Regarding representation models, the basic emotions are the most frequently recognized, especially happiness, fear, and sadness. Both single-channel and multichannel approaches are applied, with a preference for the first one. For multimodal recognition, early fusion was the most frequently applied. SVM and neural networks were the most popular for building classifiers. Qualitative analysis revealed important clues on participant group construction and the most common combinations of modalities and methods. All channels are reported to be prone to some disturbance, and as a result, information on a specific symptoms of emotions might be temporarily or permanently unavailable. The challenges of proper stimuli, labelling methods, and the creation of open datasets were also identified.

Searching for Best Predictors of Paralinguistic Comprehension and Production of Emotions in Communication in Adults With Moderate Intellectual Disability

“…Since there are various adverse effects of reduced emotion recognition abilities in people with ID, research studies aimed at detecting the predictors of these abilities may be useful, as they may result in guidelines for targeted and effective interventions. Nowadays, this kind of research is increasingly gaining importance as a support for teaching models for automatic emotion recognition, i.e., the creation of technological assistive devices that facilitate the treatment of children and adults with neurodevelopmental disorders ( Ma et al, 2019 ; Martinez-Martin et al, 2020 ; Landowska et al, 2022 ).…”

Relationship of autistic traits and the severity of fear of the COVID-19 pandemic in the general population

“…the ability to cognitively and affectively accept other people’s perspectives and understand their intentions, as well as recognise their own state of mind ( 38 ). Regardless of this, according to literature data, patients with ASD experience all emotions, including anxiety, more strongly ( 39 ), hence they may have a higher severity of fear of the COVID-19 pandemic than in the general population. People with ASD suffer from difficulties in adapting to the changing environment around them ( 40 ), which in the face of sudden changes caused by the start of the pandemic may have exacerbated their fear.…”

Facial and speech Emotional Recognition based on Improved Deep Model

“…Among its advantages is having a proportional number of files in each emotion, which avoids the problems caused by training algorithms with unbalanced data. In addition, RAVDEESS is a reference dataset in the research community that has been used in several works [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39].…”