¿Qué sabemos del robo de combustible en México? Claroscuros de un delito que no cede

Mariscal, Jacqueline Peschard; Rebolledo, María Grisel Salazar; Gómez, Octavio Augusto Olea

doi:10.22201/fcpys.2448492xe.2020.241.75273

Cited by 1 publication

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, PEMEX reported that most fuel stealing is located in the country's central area. In Mexico City alone and the five adjacent states (among which are three of the seven entities that registered the most clandestine shots), 5,420 clandestine shots were recorded the last year, equivalent to 43% according to reported in [18].…”

Section: Results Of the Geographic And Social Topics Distributionmentioning

confidence: 99%

Analysis of Open-Social Data Behavior Concerning Gasoline Stealing: A Case Study of the Mexican Petroleum Crisis

Zagal-Flores,

Mata-Rivera,

Torres-Ruiz

et al. 2023

Preprint

View full text Add to dashboard Cite

At the beginning of 2019, the petroleum crisis impacted many economies dependent on this industry. The Mexican government started programs to identify points and government officials involved in the gasoline stealing from PEMEX (Petróleos Mexicanos), the country’s leading government petroleum company. The programs consisted of supervising and monitoring the Mexican country network of gasoline ducts to detect points where gasoline was being stolen. Consequently, large urban regions faced a lack and shortage of gasoline. This situation generated several reactions in social media and many open data in news media. Although the government provided open data about stealing gasoline locations related to crimes, it did not analyze the collected data to identify patterns, insights, and the spatio-temporal characterization of this phenomenon. This paper presents a study to deal with the regional semantics described in the social media locations of gasoline stealing. Thus, a framework to discover the trends that emerge from social media and how it is correlated with the government’s open data is also presented—the proposed methodology used machine learning techniques based on linguistic and semantic technologies. The analysis was applied to a dataset of 24,317 geo-referenced tweets. The obtained results reflected the Mexican thinking opinion regarding discovered social topics, polarization maps, and regional insights. According to discovered trends, there were long fuel lines between 1.5 and 5 kilometers (on average) at fuel stations in different Mexican states.

show abstract

Section: Results Of the Geographic And Social Topics Distributionmentioning

confidence: 99%