Analysis of the minutes of rondas campesinas using text mining techniques

Quiñones Huatangari L.; Díaz Cabrera R.; Alvarado Carrasco N.; Fernández Rosillo F.; Maicelo Guevara J.L.; Cruz Caro O.; Salazar Serván S. · Frontiers in Sociology (2026) · DOI: 10.3389/fsoc.2026.1874323

Resumen

The rondas campesinas are rural community justice organizations that emerged among impoverished indigenous communities in the Andes and are the driving force behind the largest and most influential grassroots movement in north-eastern Peru. The aim of the research was to unveil the characteristics, thematic approaches and working dynamics of the rondas campesinas using text mining as a technique for information analysis. Seventy-four minutes from Huaquillas, Namballe and San Jose de Lourdes in the province of San Ignacio, department of Cajamarca were analyzed, covering the period from 2012 to 2024. The analysis included five steps: data collection and pre-processing by eliminating stopwords and tokenization, keyword identification using the word cloud technique, word quantification using the Term Frequency-Inverse Document Frequency method, latent topic analysis through Latent Dirichlet assignment and vector representation through modeling with Word2Vec. These steps allowed the identification of community problems, social control actions and emerging trends in community organization. The text mining technique is a tool to analyze minutes not only of rondas campesinas but also of organizations or institutions that want to know with certainty the thematic approaches they develop. Copyright

Instituciones: Pontificia Universidad Católica del Perú; Universidad Nacional Toribio Rodríguez de Mendoza de Amazonas; Universidad Nacional de Jaén