[DSRP Evidence](https://dsrpevidence.org/)

# Multilevel Political Connections and Interest Intermediation: Identifying Political Alliances with Social Media Data

## Details

**Authors** Lucas Gelape, Fernando Meireles, Marta Mendes da Rocha, Guilherme de Abreu Duque

**Year** 2026

**Publisher** Journal of Politics in Latin America

**Kind of work** article

**Discipline** Political Science

**Secondary disciplines** Media & Communication

**Applied** false

[Read it at the publisher](https://doi.org/10.1177/1866802X261445940) 
10.1177/1866802X261445940

## In authors' words

### Abstract

It is common, both in unitary and federal countries, for politicians at different levels to cooperate in pursuit of mutual benefits. But how can we identify who cooperates with whom to investigate the factors behind these alliances? This article proposes a novel strategy to detect alliances between local executive leaders and national legislators using mayors' social media data. Drawing on over two million posts from nearly 2000 Brazilian mayors, we develop, through a supervised machine learning model, an indicator that measures the strength of mayor-congressperson relationships. Our findings show that most connections are relatively weak, though partisanship is positively associated with stronger ties. Our approach offers a low-cost, replicable alternative to traditional methods for studying political intermediation. It advances the understanding of multilevel political dynamics in presidential systems with strong local executives and highlights the role of local elected officials as key, yet often overlooked, brokers in comparative politics.

### What they set out to do (purpose)

To develop a method for identifying and measuring the strength of cooperative alliances between local executive leaders (mayors) and national legislators.

### Who or what was studied (sample)

Over two million Facebook and Instagram posts (2018-2022) from nearly 2,000 Brazilian mayors, representing 36.5% of mayors elected in 2020.

### How they did it (methods)

Supervised machine learning classification of social media posts for brokerage activity, combined into a relationship-strength indicator based on concentration, temporal longevity, and relevance of mentions, validated against election results, campaign spending, and interviews.

### What they found (results)

Machine-learning analysis of over two million social media posts from nearly 2,000 Brazilian mayors found that most mayor-legislator relationships were weak, while shared party affiliation increased relationship strength by about 13 points (0.7 standard deviations), with geographic proximity showing a comparable effect and smaller municipalities forming stronger alliances than larger ones.

## Commentary

### In short

The findings describe a relational structure—brokerage ties between local and national levels of a political system—whose strength varies systematically with partisan and geographic factors.

**Patterns it shows** S, R

**Added** 2026-09-19

**How to cite this** Lucas Gelape, Fernando Meireles, Marta Mendes da Rocha, Guilherme de Abreu Duque (2026). Multilevel Political Connections and Interest Intermediation: Identifying Political Alliances with Social Media Data. Journal of Politics in Latin America.