Multimodal Analysis of Disagreement in Dyadic Conversations: An Approach Based on Emotion Recognition Areej Buker, Emily Smith, Olga Perepelkina, Alessandro Vinciarelli Icmi 2025 Proceedings of the 27th International Conference on Multimodal Interaction, 2025 This article proposes a multimodal approach for the detection of disagreement in dyadic conversations, where disagreement means that people express different opinions about a topic under discussion. The key-assumption underlying the work is that people tend to manifest different emotions depending on whether they are disagreeing or not. Therefore, emotions can provide evidence that disagreement is taking place. The experiments were performed over a corpus of 684 clips involving 60 dyads (120 persons and roughly 8 hours of speech). Each clip revolves around a decision-making task and it is annotated in terms of the percentage of time people spend in disagreement. For the sake of reproducibility, the Glasgow Disagreement Corpus, the data used in the experiments, has been made accessible through a link available in the paper. The results show that a multimodal approach based on language and paralanguage can predict such a percentage with Mean Absolute Error 9.7 and correlation 0.52 between actual and predicted percentage of time spent in disagreement.
Emotion Recognition for Multimodal Assessment of Attachment in School-Age Children Areej Buker, Alessandro Vinciarelli ACM International Conference Proceeding Series, 2024 Attachment is a psychological construct describing the relationship between children and their caregivers. Attachment issues lead to difficulties in the relationships with others and, as a consequence, to higher chances to have negative experiences in adult life (e.g., antisocial behaviour, mental health problems, etc.). However, early detection of attachment issues can help to attenuate the risks. For this reason, this article addresses the problem of attachment recognition in school-age children. The main novelty of the proposed approach is that it is based on emotion recognition. The motivation behind such choice is that the way people regulate their emotions is a marker of their attachment condition. In the experiments, pre-trained models based on Neural Networks were used to extract features fed to attachment classifiers capable to identify children with attachment issues. The best result (F1 Score 73.0% and Accuracy 77.9% over a corpus including 104 children) was obtained with a multimodal approach outperforming, to a statistically significant extent, unimodal methodologies based on language or paralanguage.
Multiple Instance Learning for Inference of Child Attachment From Paralinguistic Aspects of Speech Areej Buker, Huda Alsofyani, Alessandro Vinciarelli Proceedings of the Annual Conference of the International Speech Communication Association Interspeech, 2023 Attachment is a psychological construct that accounts for the way children perceive their relationship with their caregivers. Depending on the attachment condition, a child can either be secure or insecure. Identifying as many insecure children as possible is important to mitigate the negative consequences of insecure attachment in adult life. For this reason, this article proposes an attachment recognition approach that, compared to other approaches, increases the Recall, the percentage of insecure children identified as such. The approach is based on Multiple Instance Learning, a body of methodologies dealing with data represented as "bags" of feature vectors. This is suitable for speech recordings because these are typically represented as vector sequences. The experiments involved 104 participants of age 5 to 9. The results show that insecure children can be identified with Recall up to 63.3% (accuracy up to 75%), an improvement with respect to most existing models.
Comorbidities and risk factors for severe outcomes in covid-19 patients in saudi arabia: A retrospective cohort study Fatema S Shaikh, Nahier Aldhafferi, Areej Buker, Abdullah Alqahtani, Subhodeep Dey, Saema Abdulhamid, Dalal Ali Mahaii AlBuhairi, Raha Saud Abdulaziz Alkabour, Waad Sami O Atiyah, Sara Bachar Chrouf, Abdussalam Alshehri, Sunday Olusanya Olatunji, Abdullah M Almuhaideb, Mohammed S Alshahrani, Yousof AlMunsour, Vahitha B Abdul-Salam Journal of Multidisciplinary Healthcare, 2021 Purpose The first novel coronavirus disease-19 (COVID-19) case in the Kingdom of Saudi Arabia (KSA) was reported in Qatif in March 2020 with continual increase in infection and mortality rates since then. In this study, we aim to determine risk factors which effect severity and mortality rates in a cohort of hospitalized COVID-19 patients in KSA. Method We reviewed medical records of hospitalized patients with confirmed COVID-19 positive results via reverse-transcriptase-polymerase-chain-reaction (RT-PCR) tests at Prince Mohammed Bin Abdulaziz Hospital, Riyadh between May and August 2020. Data were obtained for patient’s demography, body mass index (BMI), and comorbidities. Additional data on patients that required intensive care unit (ICU) admission and clinical outcomes were recorded and analyzed with Python Pandas. Results A total of 565 COVID-19 positive patients were inducted in the study out of which, 63 (11.1%) patients died while 101 (17.9%) patients required ICU admission. Disease incidences were significantly higher in males and non-Saudi nationals. Patients with cardiovascular, respiratory, and renal diseases displayed significantly higher association with ICU admissions (p<0.001) while mortality rates were significantly higher in COVID-19 patients with cardiovascular, respiratory, renal and neurological diseases. Univariate cox proportional hazards regression model showed that COVID-19 positive patients requiring ICU admission [Hazard’s ratio, HR=4.2 95% confidence interval, CI 2.5–7.2); p<0.001] with preexisting cardiovascular [HR=4.1 (CI 2.5–6.7); p<0.001] or respiratory [HR=4.0 (CI 2.0–8.1); p=0.010] diseases were at significantly higher risk for mortality among the positive patients. There were no significant differences in mortality rates or ICU admissions among males and females, and across different age groups, BMIs and nationalities. Hospitalized patients with cardiovascular comorbidity had the highest risk of death (HR=2.9, CI 1.7–5.0; p=0.020). Conclusion Independent risk factors for critical outcomes among COVID-19 in KSA include cardiovascular, respiratory and renal comorbidities.
