Social media big data analysis for mental health research

TY - CHAP

T1 - Social media big data analysis for mental health research

AU - Wongkoblap, Akkapon

AU - Vadillo, Miguel A.

AU - Curcin, Vasa

N1 - Publisher Copyright: © 2022 Elsevier Inc. All rights reserved.

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Mental health problems are widely recognized as a major public health challenge worldwide. This highlights the need for effective tools for detecting mental health disorders in the population. Social media data is a promising source of information where people publish rich personal information that can be mined to extract valuable psychological information. However, social media data poses its own set of challenges, such as the specific terms and expressions used on different platforms, interactions between different users through likes and shares, and the need to disambiguate between statements about oneself and about third parties. Traditionally, social media natural language processing (NLP) techniques have looked at text classifiers and user classification models separately, which presents a challenge for researchers wanting not only to combine text sentiment and user sentiment analysis but also to extract user’s narratives from the textual content.

AB - Mental health problems are widely recognized as a major public health challenge worldwide. This highlights the need for effective tools for detecting mental health disorders in the population. Social media data is a promising source of information where people publish rich personal information that can be mined to extract valuable psychological information. However, social media data poses its own set of challenges, such as the specific terms and expressions used on different platforms, interactions between different users through likes and shares, and the need to disambiguate between statements about oneself and about third parties. Traditionally, social media natural language processing (NLP) techniques have looked at text classifiers and user classification models separately, which presents a challenge for researchers wanting not only to combine text sentiment and user sentiment analysis but also to extract user’s narratives from the textual content.

KW - Anaphora resolution

KW - Mental health

KW - Segmentation

KW - Social media data

KW - Tokenization

KW - Word embedding

UR - http://www.scopus.com/inward/record.url?scp=85124003713&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-822201-0.00018-6

DO - 10.1016/B978-0-12-822201-0.00018-6

M3 - Chapter

AN - SCOPUS:85124003713

SN - 9780128222027

SP - 109

EP - 143

BT - Mental Health in a Digital World

PB - Elsevier

ER -