Quantitative persona creation (QPC) has tremendous potential, as HCI researchers and practitioners can leverage user data from online analytics and digital media platforms to better understand their users and customers. However, there is a lack of a systematic overview of the QPC methods and progress made, with no standard methodology or known best practices. To address this gap and to map the field of QPC, we conduct the first systematic literature review on QPC.
We review 49 papers from 2005-2019 and make several interesting findings:
- QPC can be divided into three eras: Emergence, Diversification, and Sophistication. Over time, use of data science algorithms, data sources such as Web analytics and social media, and survey sample sizes, are increasing.
- Yet, there are very few replicative or comparative studies, so we don’t know which algorithms generate the “best” personas or even how “best” should be measured.
- Moreover, most researchers (almost none!) share their code, algorithms or data, making it difficult to achieve any clear methodological improvement or establish baselines or benchmarks.
- Most quantitative studies still use qualitative methods at one point or another: for subjective evaluation of the personas or for setting hyperparameters such as the number of personas created, for example.
- Sharing resources, such as datasets, code, and algorithms, is crucial to achieving the next stage (Maturity)
For practitioners, we provide guiding questions for assessing QPC readiness in organizations.
We thank the anonymous reviewers for their feedback that led to many improvements in the manuscript.
Read full research
Salminen, J., Guan, K., Jung, S.G., Chowdhury, S., and Jansen, B. J. (2020) A Literature Review of Quantitative Persona Creation. ACM CHI Conference on Human Factors in Computing Systems (CHI’20), Honolulu, HI, USA. 25–30 April. 1-14.
More persona research
- Is More Better?: Research Concerning the Impact of Multiple Photos on Perception of Persona Profiles
- Research on Personas: Personas and Scenarios as a Methodology for Information Sciences
- Automatic Persona Generation for Online Content Creators: Conceptual Rationale and a Research Agenda
- Research Concerning: Are Personas Done? Evaluating their usefulness in the age of digital analytics