Predicting Individual Response to a Web-Based Positive Psychology Intervention: A Machine Learning Approach.

Positive psychology interventions (PPIs) are effective at increasing happiness and decreasing depressive symptoms. PPIs are often administered as self-guided web-based interventions, but not all persons benefit from web-based interventions. Therefore, it is important to identify whether someone is likely to benefit from web-based PPIs, in order to triage persons who may not benefit from other interventions. In the current study, we used machine learning to predict individual response to a web-based PPI, in order to investigate baseline prognostic indicators of likelihood of response (N = 120). Our models demonstrated moderate correlations (happiness: r Test = 0.30 ± 0.09; depressive symptoms: r Test = 0.39 ± 0.06), indicating that baseline features can predict changes in happiness and depressive symptoms at a 6-month follow-up. Thus, machine learning can be used to predict outcome changes from a web-based PPI and has important clinical implications for matching individuals to PPIs based on their individual characteristics.

Web-Based Positive Psychology Interventions: A Reexamination of Effectiveness.

OBJECTIVE: Seligman, Steen, Park, and Peterson (2005) suggested that positive psychology interventions (PPIs) contain specific, powerful, therapeutic ingredients that effect greater increases in happiness and reductions in depression than a placebo control. This study reexamined the three PPIs that Seligman et al. found to be most effective when delivered over the internet. METHOD: Three PPIs and a placebo control, identical with the interventions used by Seligman et al., were examined in a web-based, randomized assignment design. RESULTS: Mixed-design analysis of variance and multilevel modeling showed that all interventions, including the placebo, led to significant increases in happiness and reductions in depression. The effects of PPIs were indistinguishable from those of the placebo control. CONCLUSION: Using web-based delivery, both PPIs and theoretically neutral placebos can increase happiness and reduce depression in self-selected populations. Possible explanations include that non-specific factors common to most therapeutic treatments are responsible for the observed changes, or that cultural or other context-related variables operate to account for the divergent findings.

Scoring the VIA Survey of Character.

The VIA Survey of Character (VIA) is a self-report inventory designed to measure and assess 24 character strengths that are linked conceptually to six fundamental "virtues"--Wisdom and Knowledge, Courage, Humanity, Justice, Temperance, and Transcendence, as developed by Peterson and Seligman in 2004. Despite its popularity, the current presentation of the VIA is not easy to score; researchers must either use a limited online scoring facility or must use outdated scoring keys. This paper presents a full description of the scoring key.