Related Experiment Videos
How do recommender systems learn political opinions? A semi-synthetic step-by-step experiment
Tim Faverjon1,2, Jean-Philippe Cointet1, Pedro Ramaciotti1,2,3
1médialab Sciences Po, Paris, France.
Plos One
|May 26, 2026
Summary
Social media algorithms create spatial representations of user ideology using minimal data, impacting content diets. This study explains how these ideological structures form and affect user exposure to information.
Area of Science:
- Computational Social Science
- Algorithm Explainability
- Social Media Analysis
Background:
- Social media recommendations significantly influence user information consumption, potentially leading to political segregation.
- Existing research highlights ideological structures in algorithmic representations but lacks causal explanations for their formation.
Purpose of the Study:
- To provide a step-by-step causal explanation for how social media recommenders create geometrical representations of user ideology.
- To investigate the impact of these ideological representations on user content diets.
- To analyze the trade-offs between political leaning, diversity, and relevance in recommendations when ideological representations are modified.
Main Methods:
- Utilized an algorithm explainability approach on a dataset of nearly 40,000 X (formerly Twitter) users and their shared content.
- Trained a recommendation model on real-world platform data to compute synthetic recommendations.
- Analyzed the spatial representation of user ideological positions within the recommender system.
Main Results:
- Demonstrated that basic recommendation principles, trained on content dissemination data, inherently generate a spatial Left-Right ideological representation of users.
- This ideological mapping is independent of user demographics like age and gender.
- Modifying these ideological representations revealed trade-offs in recommendation outcomes regarding political leaning, content diversity, and relevance.
Conclusions:
- Social media algorithms inadvertently construct user ideological profiles through fundamental recommendation mechanisms.
- Understanding the causal formation of these profiles is key to addressing concerns about algorithmic bias and political segregation.
- The study offers insights into manipulating recommendation systems to balance ideological representation, content diversity, and relevance.
Related Concept Videos
00:52Social Proof
Social proof is a form of persuasion based on comparison and conformity. People compare their behavior and actions to what others are doing and will change to conform to do what their peers do.
01:22Purposive Learning
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a bonus...
01:31Confirmation Biases
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
01:52Persuasion Strategies
Researchers have tested many persuasion strategies, including the foot-in-the door and the door-in-the-face techniques, in a variety of contexts. Ultimately, the principles are effective in selling products and changing people’s attitude, ideas, and behaviors (Cialdini & Goldstein, 2004).
02:40The Scientific Method
Research is what makes the difference between facts and opinions. Facts are observable realities, and opinions are personal judgments, conclusions, or attitudes that may or may not be accurate. In the scientific community, facts can be established only using evidence collected through empirical research.
01:13Randomized Experiments
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...