Related Experiment Video
Updated: Sep 1, 2025
12:08
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
Published on: August 13, 2014
24.6K
Big Data, Small Personas: How Algorithms Shape the Demographic Representation of Data-Driven User Segments.
Joni Salminen1, Kamal Chhirang2, Soon-Gyo Jung1
1School of Marketing and Communication, University of Vaasa, Finland.
Big Data
|August 15, 2022
Summary
Algorithmic bias in user segmentation can lead to unfair or unrepresentative personas. Spectral Embedding best balances diversity, fairness, and consistency in persona creation.
Area of Science:
- Computer Science
- Data Science
- Human-Computer Interaction
Background:
- Algorithmic bias is a concern in data-driven user segmentation.
- Creating user personas can lead to issues with fairness, diversity, and consistency.
Purpose of the Study:
- To compare different algorithms for user persona creation.
- To evaluate personas based on fairness, diversity, and consistency.
Main Methods:
- Collected 363 million video views from a global news organization.
- Applied various algorithms to generate user personas.
- Analyzed personas for fairness, diversity, and consistency metrics.
Main Results:
- Algorithms grouped into low diversity-high fairness and high diversity-low fairness.
- High diversity correlated negatively with fairness (Spearman's correlation: -0.83).
- Spectral Embedding demonstrated the best balance across all metrics.
Conclusions:
- Algorithm choice significantly impacts user persona demographics and decision-making.
- Ethical considerations are crucial for data-driven user segmentation.
- Spectral Embedding is a promising algorithm for balanced persona generation.
Related Concept Videos
01:16Stratified Sampling Method
12.6K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a stratified sample, divide the population into groups called strata and then take a...
To choose a stratified sample, divide the population into groups called strata and then take a...
12.6K
02:01Group Design
9.5K
The most basic experimental design involves two groups: the experimental group and the control group. The two groups are designed to be the same except for one difference— experimental manipulation. The experimental group gets the experimental manipulation—that is, the treatment or variable being tested—and the control group does not. Since experimental manipulation is the only difference between the experimental and control groups, we can be sure that any differences between...
9.5K
01:22Applications of Life Tables
110
Life tables are versatile across various fields, providing a quantitative basis for analyzing mortality and survival rates. Whether used by demographers, actuaries, epidemiologists, or sociologists, life tables offer valuable insights into the dynamics of life and death, facilitating informed decisions in public health, insurance, conservation, and beyond. Their broad applicability highlights the interconnectedness of demographic data with practical outcomes in everyday life and strategic...
110
01:12Analysis of Population Pharmacokinetic Data
371
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
371
01:20Cluster Sampling Method
12.5K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
12.5K
03:33Genetic Drift
40.6K
Natural selection—probably the most well-known evolutionary mechanism—increases the prevalence of traits that enhance survival and reproduction. However, evolution does not merely propagate favorable traits, nor does it always benefit populations.
40.6K