Fortschritte und Herausforderungen für die Analyse von Big Data in sozialen Medien im Jugendalter
Abstract
Zusammenfassung. Für Jugendliche sind soziale Medien allgegenwärtig und sie verwenden sie, um ihren Gedanken, Gefühlen und Verhaltensweisen Ausdruck zu verleihen. Entsprechend bietet sich mit neuen interdisziplinären Methoden die Möglichkeit, die in sozialen Netzwerken vorhandenen Massendaten (Big Data) automatisch und maschinell zu analysieren, um darin Indikatoren für psychische Auffälligkeiten und Störungen im Sinne von Abweichungen von den üblichen Aktivitäts- und Kommunikationsmustern zu identifizieren. Diese Übersichtsarbeit gibt zunächst eine Einführung in das Konzept und mögliche Anwendungsbereiche von Big Data in sozialen Medien. Darauf aufbauend werden die ersten Studien diskutiert, die mittels dieser Analysen psychische Auffälligkeiten im Jugendalter entdecken konnten, da sich Unterschiede in der Struktur der sozialen Netzwerke, in der Verwendung von Wörtern und in der Kommunikation von Meinungen und Gefühlen fanden. Der Einbezug einer Vielzahl von Messzeitpunkten für die Modellierung intraindividueller Veränderungen könnte künftig in Kombination mit Mediatoranalysen helfen, besser zu verstehen, wann und durch welche Mechanismen sich der Konsum sozialer Medien auf die psychische Gesundheit auswirkt. Künftige Studien sollten zudem durch die Berücksichtigung weiterer Störungsbilder und Informationsquellen, verschiedener Altersgruppen und zusätzlicher sozialer Netzwerke zur Entwicklung von genaueren Prädiktionsmodellen zur Früherkennung psychischer Störungen in dieser Altersgruppe beitragen und darauf abgestimmte personalisierte Interventionen zur Förderung der psychischen Gesundheit und Resilienz anbieten.
Abstract. Social media are ubiquitous today, and adolescents use them to express their thoughts, feelings, and behaviours. New interdisciplinary methods allow the automatic analysis of the massive amounts of data (big data) available on social networking websites using machine-learning tools to detect indicators of mental-health problems and disorders by identifying differences with common activity and communication patterns. This review first introduces the concept and potential fields of applications of big data in social media. It then discusses the first studies that used big data analyses and detected mental-health problems by identifying differences in the structure of social networks, in the use of certain words, and in the communication of opinions and sentiments. Future studies employing several assessment points could use longitudinal mediation analysis to model intraindividual changes in order to understand when and through which mechanisms social media use has an impact on mental health. Furthermore, future studies should include additional mental disorders, various sources of information, a broader age range, and additional social-networking websites to develop more precise models for the early detection of mental disorders. This would enable the development of personalised intervention programs to promote mental health and resilience in adolescents.
Literatur
2015). The Role of Social Network Technologies in Online Health Promotion: A Narrative Review of Theoretical and Empirical Factors Influencing Intervention Effectiveness. Journal of Medical Internet Research, 17, e141.
(2018). Big data and machine learning in health care. JAMA, 319, 1317–1318.
(2016). Social big data: Recent achievements and new challenges. Information Fusion, 28, 45–59.
(2006). Pattern recognition and machine-learning. New York: Springer.
(2017). Signal processing and machine learning for mental health research and clinical applications. IEEE Signal Processing Magazine, 34, 188–195.
(2014). Data-intensive applications, challenges, techniques and technologies: A survey on Big Data. Information Sciences, 275, 314–347.
(2009). Information disclosure and control on Facebook: Are they two sides of the same coin or two different processes. Cyberpsychology and. Behavior, 12, 341–345.
(2018). Media use and brain development during adolescence. Nature Communications, 9, 1–10.
(2017). Artificial intelligence-assisted online social therapy for youth mental health. Frontiers in Psychology, 8, 796.
(2017). Benefits and Risks of Machine Learning Decision Support Systems. JAMA, 318, 2356.
(2015). Beyond the hype: Big data concepts, methods, and analytics. International Journal of Information Management, 35, 137–144.
(2012, IT glossary, www.gartner.com/it-glossary/big-data, abgerufen am 05.04.2018.
,2017). Detecting depression and mental illness on social media: An integrative review. Current Opinion in Behavioral Sciences, 18, 43–49.
(2017). Help seeking for mental health problems in an adolescent population: The effect of gender. Journal of Mental Health, Jul 18, 1–8.
(2018). Machine learning for the quantified self. On the art of learning from sensory data. Cham: Springer International Publishing.
(2011). A survey on visual content-based video indexing and retrieval. IEEE Transaction on Systems, Man, and Cybernetics – Part C: Applications and Reviews, 41, 797–819.
(2016). Data mining techniques in social media: A survey. Neurocomputing, 214, 654–670.
(2013). „Facebook depression?“ Social networking site use and depression in older adolescents. Journal of Adolescent Health, 52, 128–130.
(2015). Machine learning: Trends, perspectives, and prospects. Science, 349, 255–260.
(2015).
(Adolescent development and psychological mechanisms in interactive media use . In S. S. Sundar (Ed.), The Handbook of Psychology of Communication Technology (pp. 332–364). Hoboken: Wiley-Blackwell.2016). Mining big data to extract patterns and predict real-life outcomes. Psychological Methods, 21, 493–506.
(2001). 3D Data Management: Controlling data volume, velocity and variety. Application Delivery Strategies META Group, 949.
(2017). Analyzing and identifying teen`s stressful periods and stressors events from a microblog. IEEE Journal of Biomedical and Health Informatics, 21, 2168–2194.
(2018). A bibliometric analysis and visualization of medical big data research. Sustainability, 10, 166.
(2018). Monitoring freshman college experience through content analysis of tweets: Observational study. JMIR Public Health and Surveillance, 4, e5.
(2017). Using real-time social media technology to monitor levels of perceived stress and emotional state in college students: A web-based questionnaire study. JMIR Mental Health, 4, e2.
(2017). Children’s privacy in the big data era: Research opportunities. Pediatrics, 140, 117–121.
(2011). The impact of social media on children, adolescents, and families. Pediatrics, 127, 800–804.
(2010).
(„Cry baby“: Using spectrographic analysis to assess neonatal health status from an infant’s cry . In A. Neustein (Ed.), Advances in speech recognition: Mobile environments, call centers and clinics (pp. 324–348). New York: Springer.2016). Children and adolescents and digital media. Pediatrics, 138, e20162593.
. (2017). A social spin on language analysis. Nature, 545, 166–167.
(2016). Transdiagnostische Ansätze in der Psychotherapie. Zeitschrift für Kinder- und Jugendpsychiatrie und Psychotherapie, 44, 417–420.
(2016). Modulare Psychotherapie mit Kindern und Jugendlichen. Zeitschrift für Kinder- und Jugendpsychiatrie und Psychotherapie, 44, 467–478.
(2016). Die Vierte Industrielle Revolution. München: Pantheon.
(2016). Social networking sites, depression, and anxiety. JMIR Mental Health, 3, e50.
(2014). Growing up wired: Social networking sites and adolescent psychosocial development. Clinical Child and Family Psychological Review, 17, 1–18.
(2017). Critical analysis of big data challenges and analytical methods. Journal of Business Research, 70, 263–286.
(2016). Data mining of web-based documents on social networking sites that included suicide-related words among Korean adolescents. Journal of Adolescent Health, 59, 668–673.
(2017). How ICT savvy are digital natives actually? Nordic Journal of Digital Literacy, 12(3), 89–108.
(2016). Research ethics in an age of big data. Bulletin of the Association for Information Science and Technology, 42, 2–37.
(2012). Social networking site use predicts changes in young adults’ psychological adjustment. Journal of Research on Adolescence, 22, 453–466.
(2014). Big questions for social media big data: Representativeness, validity and other methodological pitfalls. Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media, 505–514.
(2017). Social media use and access to digital technology in US young adults in 2016. Journal of Medical Internet Research, 19, e196.
(2016).
(Using social media to measure student wellbeing: A large-scale study of emotional response in academic discourse . In E. Spiro & Y. Y. Ahn (Eds.). Social Informatics. SocInfo 2016. Lecture Notes in Computer Science, 10046 (pp. 510–526). Cham: Springer International Publishing.2017). Detecting and characterizing eating-disorder communities on social media. Tenth ACM International Conference on Web Search and Data Mining – WSDM 2017, 91–100.
(2017). Researching mental health disorders in the era of social media: Systematic review. Journal of Medical Internet Research, 19, e228.
(2018). The Forth Industrial Revolution: Opportunities and challenges. International Journal of Financial Research, 9, 90–95.
(