Online Social Support Detection in Spanish Social Media Texts

2025-02-10

AI Summary

This work addresses the scarcity of research on online social support identification in Spanish-language social media. We introduce the first fine-grained annotated dataset comprising 3,189 YouTube comments and formally define “social support detection” as a novel computational task. To mitigate class imbalance, we propose a GPT-4o–assisted data balancing method and empirically demonstrate its critical impact on recognizing six fine-grained support subtypes (e.g., individual/group, national/minority). Through systematic evaluation across traditional machine learning, LSTM, BERT, and GPT-4o zero-shot inference, we show that balanced data consistently improves performance across all models; notably, GPT-4o achieves state-of-the-art accuracy on the primary binary classification task (support vs. non-support). This study fills a key gap in positive content analysis for Spanish, providing both a foundational dataset and methodological framework to advance healthy online community development.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Humanities & Computational Social Science
• Machine Learning: Evaluation and Analysis

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

The advent of social media has transformed communication, enabling individuals to share their experiences, seek support, and participate in diverse discussions. While extensive research has focused on identifying harmful content like hate speech, the recognition and promotion of positive and supportive interactions remain largely unexplored. This study proposes an innovative approach to detecting online social support in Spanish-language social media texts. We introduce the first annotated dataset specifically created for this task, comprising 3,189 YouTube comments classified as supportive or non-supportive. To address data imbalance, we employed GPT-4o to generate paraphrased comments and create a balanced dataset. We then evaluated social support classification using traditional machine learning models, deep learning architectures, and transformer-based models, including GPT-4o, but only on the unbalanced dataset. Subsequently, we utilized a transformer model to compare the performance between the balanced and unbalanced datasets. Our findings indicate that the balanced dataset yielded improved results for Task 2 (Individual and Group) and Task 3 (Nation, Other, LGBTQ, Black Community, Women, Religion), whereas GPT-4o performed best for Task 1 (Social Support and Non-Support). This study highlights the significance of fostering a supportive online environment and lays the groundwork for future research in automated social support detection.

Problem

• Detecting online social support in Spanish texts
• Creating a balanced dataset using GPT-4o
• Evaluating model performance on balanced datasets

Innovation

• GPT-4o generated paraphrased comments
• Transformer model evaluated dataset performance
• First annotated dataset for Spanish social support