Automatic Detection in Twitter of Non-Traumatic Grief Due to Deaths by COVID-19: A Deep Learning Approach

• Published in: IEEE access Vol. 11; pp. 143402 - 143416
• Main Authors: Mata-Vazquez, Jacinto, Pachon-Alvarez, Victoria, Gualda, Estrella, Araujo-Hernandez, Miriam, Garcia-Navarro, E. Begona
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Blogs; COVID-19; Deep learning; Digital media; Fatalities; Hyperparameter optimization; hyperparameters; Messages; non-traumatic grief detection; Pandemics; Social networking (online); Social networks; Task analysis; Transformers; Twitter
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3343149

Non-traumatic grief can be defined as, a complex process that includes emotional, physical, spiritual, social, and intellectual behaviors and responses through which individuals, families, and communities incorporate actual, anticipated, or perceived loss into their daily lives. In the age of widespread social media usage, individuals frequently share their emotions online for various reasons. This was particularly evident during the peak of the COVID-19 pandemic and its aftermath, where many social media interactions replaced or supplemented traditional farewell and mourning practices, including communications related to deaths. Recognizing messages expressing non-traumatic grief is a crucial challenge for nursing, medicine, and socio-health interventions. This awareness could assist specialists in improving early prevention and healthcare measures. In this work we present an approach to automatically detect messages (tweets) containing non-traumatic grief by means of deep learning techniques. To this end, a corpus of Spanish-language tweets has been built using a binary label to indicate the presence or absence of non-traumatic grief and has been released for use in future research. To address this challenge, multiple monolingual and multilingual language models based on pre-trained Transformer models have been fine-tuned, performing an exhaustive search to obtain the best hyperparameter values. Through this approach and employing various oversampling and undersampling techniques to mitigate the dataset's imbalance issue, the trained models reached very good results on different evaluation metrics, achieving an accuracy, AUC-ROC, and F-measure of 0.850, 0.836, and 0.827, respectively. Our results show the significance of hyperparameter selection during the learning process and demonstrate the potential of deep learning approaches for detecting non-traumatic grief messages.