☆ 4.7 Article

Depression detection for twitter users using sentiment analysis in English and Arabic tweets

ARTIFICIAL INTELLIGENCE IN MEDICINE (2024)

Deep Learning for Depression Detection Using Twitter Data

Doaa Sami Khafaga et al.

Summary: Social media plays a significant role in communication, allowing people to share their emotions with others. Identifying depressed individuals based on their messages is crucial for early detection and intervention. Existing methods for depression prediction lack accurate definitions, but the proposed MDHAN approach combines deep learning and feature selection techniques to improve classification accuracy. Experimental results demonstrate that MDHAN achieves better performance in terms of accuracy, precision, recall, and F1-measure compared to other existing methods, with shorter execution time.

INTELLIGENT AUTOMATION AND SOFT COMPUTING (2023)

添加到收藏夹

Article Computer Science, Theory & Methods

Big data analytics on social networks for real-time depression detection

Jitimon Angskun et al.

Summary: This study proposes a real-time depression detection method based on big data analytics by analyzing demographic characteristics and opinions of social media users. Machine learning techniques were used to construct the detection model, with the Random Forest technique achieving higher accuracy in detecting depression.

JOURNAL OF BIG DATA (2022)

添加到收藏夹

Review Health Care Sciences & Services

Detecting Depression Signs on Social Media: A Systematic Literature Review

Rafael Salas-Zarate et al.

Summary: This review examines research on depression sign detection from social media conducted between 2016 and mid-2021. The study found that Twitter was the most studied social media platform, word embedding was the most prominent linguistic feature extraction method, support vector machine was the most used machine-learning algorithm, Python libraries were the most popular computing tools, and cross-validation was the most common statistical analysis method.

HEALTHCARE (2022)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems