Major life events from adolescence to young adulthood: A longitudinal natural language processing analysis of a large urban cohort

Large-scale population-based studies of factors that pose a risk or protect youth from mental health problems rarely assess young people’s first-hand experiences in their own words. This longitudinal study analyzed youths’ self-reported major life events, and examined how the key topics changed from mid-adolescence to young adulthood. N=1,442 participants from an urban multiethnic cohort reported their most important life events at ages 15, 17, 20, and 24 in open-text segments. Themes in N=5,670 descriptions were analyzed using topic modeling with the Python library BERTopic. The reported events were mostly of positive valence (83.1%), spanned diverse life domains (education and career development, social relationships, leisure activities and successes, mental health and well-being, and other life transitions and independence), and shifted from mid-adolescence to adulthood. Despite their significance, many events deemed most important by young people are not necesarilly included in risk and resilience studies. The study highlights how longitudinal population-based research can draw on open-text data and employ NLP techniques to assess youths’ lived experiences. Many reports of positive life events suggest that an increased focus on promoting beneficial experiences may be needed to promote youth mental health, in addition to supporting youth in coping with stressful life events and resolving developmental tasks.