Categories
Persona Thinking Personas

Connected Personas: Primary, Secondary, Served, and Anti-Personas

Often, people think of personas as a one-layered concept. Meaning, there is only one set of personas they consider. This set is typically the current customers (e.g., most loyal or most valuable) or potential customers (e.g., those currently served by the competitors).

However, an interesting alternative is to consider personas in a connected way. Meaning, there are many persona sets that are inter-related.

  • Primary personas = these are the main targets of decision-making, i.e., the customers or users of a product. For example, the highest-paying customers.
  • Secondary personas = these are personas that have additional needs for which you can adjust the product or service, without harming the experience of the primary personas. For example, visually impaired users (e.g., you can increase the font size without it affecting negatively the user experience of primary users — many accessibility best practices fall into this category).
  • Served personas = these are personas that are not customers or users of your company, but are affected by the use of the product. For example, say your personas describe receptionists at a hotel. Served personas would be the customers of the receptionists. Essentially, the clients of your client.
  • Anti-personas = these are users or customers that are not the users of the product or services of your company, and are not directly affected by the product either. For example, a hotel cleaner would most likely not be affected by the work of the receptionist directly. Sometimes, thinking of who the persona is not helps flesh out the parts that make the persona unique.

In conclusion, prioritization is needed to focus on one persona set at a time. Simultaneously, it is important to aknowledge that other persona sets also exist. To visually represent different persona sets and their connections (especially between primary, secondary, and served personas), one can create a persona map, which a diagram that shows the connections of the different persona sets.

Categories
Persona Research

Rethinking Personas for Fairness: Algorithmic Transparency and Accountability in Data-Driven Personas

Algorithmic fairness criteria for machine learning models are gathering widespread research interest. They are also relevant in the context of data-driven personas that rely on online user data and opaque algorithmic processes. 

Overall, while technology provides lucrative opportunities for the persona design practice, several ethical concerns need to be addressed to adhere to ethical standards and to achieve end user trust. 

Rethinking Personas for Fairness: Algorithmic Transparency and Accountability in Data-Driven Personas
Rethinking Personas for Fairness: Algorithmic Transparency and Accountability in Data-Driven Personas

In this research, led by Joni Salminen, we outline the key ethical concerns in data-driven persona generation and provide design implications to overcome these ethical concerns. 

Good practices of data-driven persona development include (a) creating personas also from outliers (not only majority groups), (b) using data to demonstrate diversity within a persona, (c) explaining the methods and their limitations as a form of transparency, and (d) triangulating the persona information to increase truthfulness.

Salminen, J., Jung, S.G., Chowdury, S.A., and Jansen, B. J. (2020) Rethinking Personas for Fairness: Algorithmic Transparency and Accountability in Data-Driven Personas. 22nd International Conference on Human-Computer Interaction (HCII2020). Copenhagen, Denmark, 19-24 July 2020. 82-100.

Categories
Persona Research

Enriching Social Media Personas with Personality Traits: A Deep Learning Approach Using the Big Five Classes

In research led by Jon Salminen, to predict the personality traits of data-driven personas, we apply an automatic persona generation methodology to generate 15 personas from the social media data of an online news organization.

nriching Social Media Personas with Personality Traits: A Deep Learning Approach Using the Big Five Classes
Enriching Social Media Personas with Personality Traits: A Deep Learning Approach Using the Big Five Classes

After generating the personas, we aggregate each personas’ YouTube comments and predict the “Big Five” personality traits of each persona from the comments pertaining to that persona.

For this, we develop a deep learning classifier using three publicly available datasets. Results indicate an average performance increase of 4.84% in F1 scores relative to the baseline.

We then analyze how the personas differ by their detected personality traits and discuss how personality traits could be implemented in data-driven persona profiles, as either scores or narratives.

Salminen, J., Rao, R.G., Jung, S.G., Chowdury, S.A., and Jansen, B. J. (2020) Enriching Social Media Personas with Personality Traits: A Deep Learning Approach Using the Big Five Classes. 22nd International Conference on Human-Computer Interaction (HCII2020). Copenhagen, Denmark, 19-24 July 2020. 101-120.

Categories
Persona Creation

A Template for Data-Driven Personas: Analyzing 31 Quantitatively Oriented Persona Profiles

Template for Data-Driven Personas: Analyzing 31 Quantitatively Oriented Persona Profiles

Following the proliferation of personified big data and data science algorithms, data-driven user personas (DDPs) are becoming more common in persona design.

However, the DDP templates are seemingly diverse and fragmented, prompting a need for a synthesis of the information included in these personas.

In this research, led by Joni Salminen, analyzing 31 templates for DDPs, we find that DDPs vary greatly by their information richness, as the most informative layout has more than 300% more information categories than the least informative layout.

We also find that graphical complexity and information richness do not necessarily correlate. Furthermore, the chosen persona development method may carry over to the information presented, with quantitative data typically presented as scores, metrics, or tables and qualitative data as text-rich narratives.

We did not find one “general template” for DDPs and defining this is difficult due to the variety of the outputs of different methods as well as different information needs of the persona users.

Salminen, J., Guan, K., Nielsen, L., Jung, S.G., and Jansen, B. J. (2020) A Template for Data-Driven Personas: Analyzing 31 Quantitatively Oriented Persona Profiles. 22nd International Conference on Human-Computer Interaction (HCII2020). Copenhagen, Denmark, 19-24 July 2020. 125-144