Social support detection from social media texts
PLOS One · 2026
DOI: 10.1371/journal.pone.0337476 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Zahra Ahani und 6 weiteren Autor:innen. Beteiligte Einrichtung: Instituto Politécnico Nacional (IPN), Centro de Investigación en Computación (CIC), Mexico City, Mexico. Hauptthemen laut MEDLINE: Social Media, Social Support. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Conacyt, SecretarÃa de Investigación y Posgrado of the Instituto Politécnico Nacional, Mexico.
Abstract (Originalsprache)
Social support, conveyed through a multitude of interactions and platforms such as social media, plays a pivotal role in fostering a sense of belonging, aiding resilience in the face of challenges, and enhancing overall well-being. This paper introduces Social Support Detection (SSD) as a Natural Language Processing (NLP) task aimed at identifying supportive interactions within online communities. We define SSD through three subtasks: (1) binary classification of whether a comment expresses social support or not social support, (2) binary classification of the intended support target (individual or group), and (3) multiclass classification of the specific group being supported, including Nation, Other, LGBTQ, Black Community, Religion, and Women. We conducted experiments on a manually annotated dataset of 9,998 YouTube comments. Traditional machine learning models were employed using various combinations of linguistic, psycholinguistic, emotional, and sentiment-based features. Additionally, neural network-based models incorporating word embeddings were evaluated to enhance performance across the subtasks. The results indicate a prevalence of group-oriented support in online discourse, highlighting broader societal dynamics. The findings show that integrating psycholinguistic and affective features with unigram representations improves classification performance. The best macro F1-scores achieved across the subtasks range from 0.72 to 0.82.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Instituto Politécnico Nacional (IPN), Centro de Investigación en Computación (CIC), Mexico City, Mexico.
- Tecnologico de Monterrey, Escuela de Ingenieria y Ciencias, Mexico City, Mexico.
ORCID-Profile: Moein Shahiki Tash, Grigori Sidorov, Rau L Monroy
Förderung
- Conacyt
- SecretarÃa de Investigación y Posgrado of the Instituto Politécnico Nacional, Mexico
Zitieren
APA
Ahani, Z., Shahiki Tash, M., Balouchzahi, F., Ramos, L., Sidorov, G., Gelbukh, A., & Monroy, R. L. (2026). Social support detection from social media texts. PLOS One. https://doi.org/10.1371/journal.pone.0337476
Vancouver
Ahani Z, Shahiki Tash M, Balouchzahi F, Ramos L, Sidorov G, Gelbukh A, et al. Social support detection from social media texts. PLOS One. 2026. doi:10.1371/journal.pone.0337476
BibTeX
@article{Ahani2026,
author = {Ahani, Zahra and Shahiki Tash, Moein and Balouchzahi, Fazlourrahman and Ramos, Luis and Sidorov, Grigori and Gelbukh, Alexander and Monroy, Rau L},
title = {Social support detection from social media texts},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0337476}
}
EUVIMED