Categories
Data-Driven Personas Persona Analytics Persona Creation Persona System Personas

APG: A Data-Intensive Persona System

APG is a data-intensive system that automatically creates rich personas representing customer segments by employing web/social media analytics.

Here is an example of an APG persona.

Here is an example of an APG persona.
Here is an example of an APG persona.

APG uses this analytics data to identify customer behaviors, generates customer segments, and then enriches these customer segments with gender, age, and nationality appropriate names and pictures; customer loyalty rating, customer interests, product interactions, brand sentiment, and segment sizes represented by the personas, … all done in a privacy-preserving process using only aggregated data.

So, APG is an exceptionally data-intensive system!

How data-intensive?

Here is APG by the numbers! (as of 18 May 2020)

The APG system has more than:

  • 1.5K images for personas, copyrights purchased or common use license and meta tagged with gender-age-nationality
  • 1M unique names for personas, meta tagged with name-age-nationality
  • 178,340 personas generated for current clients over a more than three year period
  • 17,465 persona sets (different number of personas, different type of personas (for the month (country), for the month (region), lifetime (country), lifetime (region))
  • 621 generations of persona sets

The APG system has identified more than: 8M customer segment sizes (i.e., customer segments represented by personas)

The APG system leverages more than:

  • 599K pieces of contents from multiple data sources (currently YouTube, Facebook, Twitter, Instagram, and Google Analytics)
  • 28M content comments from multiple data sources (currently  YouTube, Facebook, Twitter, and Instagram)

The APG system, for user engagement measures, leverages more than:

  • 205M likes from Instagram
  • 28M comments from multiple data sources (YouTube, Facebook, Twitter, and Instagram)

The APG system, for appropriate name generation and meta-tagging, leverages more than: 5M publicly available online profiles.

Data-intensive! Data-driven personas!

Read more

Jansen, B. J., Salminen, J., and Jung, S.G. (2020) Data-Driven Personas for Enhanced User Understanding: Combining Empathy with Rationality for Better Insights to AnalyticsData and Information Management. 4(1), 1-17.  https://content.sciendo.com/view/journals/dim/4/1/article-p1.xml

Categories
CHI Data-Driven Personas Persona Research Personas

The Ethics of Data-Driven Personas

Quantitative data and algorithms are becoming more common for persona creation, but it is not clear to which extent this data and opaque machine learning algorithms introduce bias at various steps of data-driven persona creation (DDPC) and/or violate user rights.

The Ethics of Data-Driven Personas
The Ethics of Data-Driven Personas

In this conceptual work, led by Joni Salminen, we use Gillespie’s framework of algorithmic ethics to analyze DDPC for ethical considerations.

Categories
Data-Driven Personas Personas

Do your think your personas are stable? They probable aren’t!

two rocks on a rock = stability
Capturing the Change in Topical Interests of Personas Over Time

In this research, we collect monthly content consumption and demographic data from YouTube over two years for a large media publisher.

We use automation to generate 15 personas each month. Then, we examine the consistency of the generated personas over time. We find that there are 35 unique personas in total for the entire period. The change in personas reflect the changes in the underlying audience population.

For each persona, we generate topics of interest. We then identify the top three monthly topics for each of the 35 personas following an identical algorithmic approach each month. For this, we use the APG system.

We then compare the sets of topical interests of the personas month-over-month for the entire two-year period. Findings show that there is an average 20.2% change in topical interests. Findings also show that 68% of the personas experience more topical change than topical consistency.

Results suggest that the topical interests of online audiences are fluid. These changes in the underlying audience data can occur within a relatively short period, resulting in the need for constant updating of personas using data-driven methods.

The implications for organizations seeking to understand their online audience are that they should employ routine data analysis to detect changes in the audience interests and investigate ways to automate their persona generation processes.

Read full research

Jansen, B. J., Jung, S.G., and Salminen, J. (2019) Capturing the Change in Topical Interests of Personas Over Time. Association for Information Science and Technology Annual Meeting 2019 (ASIST2019). Melbourne, Australia. 19-23 Oct. 127-136.

Read more persona research

All published work from us: https://persona.qcri.org/persona-research

Read more about data-driven personas

What is a Data-Driven Persona?

Introduction to Data-Driven Personas

Giving Faces to Data by Creating Data-Driven Personas

Benefits of Data-Driven Personas

Explaining Data-Driven Personas to End Users

Got too many personas? This approach can help!

 

Categories
Data-Driven Personas Persona Creation Personas

What is a Data-Driven Persona?

A data-driven persona is derived from verifiable facts about the represented segment of the target population in sufficient amount for quantitative analysis.

An ideal persona is a proxy for a person. The person is the targeted user group, audience, or customer segment. An ideal persona both describes a segment and predicts the segment behavior.

Jansen, B. J., Salminen, J., and Jung, S.G. (2020) Data-Driven Personas for Enhanced User Understanding: Combining Empathy with Rationality for Better Insights to AnalyticsData and Information Management. 4(1), 1-17.  https://content.sciendo.com/view/journals/dim/4/1/article-p1.xml

Read more about data-driven personas

Introduction to Data-Driven Personas

Giving Faces to Data by Creating Data-Driven Personas

Benefits of Data-Driven Personas

Explaining Data-Driven Personas to End Users

Got too many personas? This approach can help!

Do your think your personas are stable? They probable aren’t!