In Colombia, one of the biggest challenges for the oil and gas industry is to generate a sound reputation and a new perception about its benefits to the communities located in the area of influence. Even though, the oil and gas industry generates between 9 to 11% of the Gross Domestic Product (GDP) in Colombia, there is a negative perception of local communities due to the impacts of the operations of the industry on the people and environment; as a consequence, the implementation of pedagogical methodologies to educate communities about the sustainable view of the modern Oil and gas Industry, and the importance to the access to energy and water is a need. In this sense, programs such as Energy4Me and PetrolCopa Reto Escolar have been implemented over the last two years in different regions of Colombia, which have allowed the collection of a considerable amount of data with great technical and social value from more than 10000 participants. This information has been refined, processed and analyzed to show how data science generates added value in the continuous improvement of the methodologies implemented by the data center of SPE Colombian Section; thus, improving relationship between industry and local communities through a fluent communication and knowledge channel. The analysis of the information and its implementation in these educational programs was carried out through the application of different statistical methods and digital tools for processing and monitoring information, which resulted in the design of optimal processes for the collection of structured and unstructured data such as; community behavior parameters, social problems, demographic characteristics and acquired technical knowledge. This process took into account at the same time other related variables such as the heterogeneity of rural communities, logistical and operational challenges and the social conditions of each region. The data gathering process involved 500 volunteers in more than 5000 people from different regions, ethnic groups, ages, gender and level of education. Once the information was correlated and the methodological approach of the programs improved, trends and direct relationships were established between the data analyzed and the decrease in the rate of rejection by the communities towards Oil and Gas industry in the study regions.