Social media platforms provide easy access to the public opinion (called electronic word-of-mouth), which can be collected and analyzed to extract knowledge about the reputation of an organization. Monitoring this reputation in the public sector may bring several benefits for its institutions, especially in supporting decision-making and developing marketing campaigns. Thus, to offer a solution aimed at the needs of this sector, the goal of this research was to develop a methodology capable of extracting relevant information about eWOM in social media, using text mining and natural language processing techniques. Our goal was achieved through a methodology capable of handling the small amount of information regarding public state organizations in social media. Additionally, our work was validated using the context of the Portuguese Army and revealed the potential to provide indicators of institutional reputation. Our results present one of the first cases of the application of this type of techniques to an Army organization and to understand its negative reputation among the population.

--

eWOM,Public sector,Reputation,Social media,Voluntary service

• Ciências da Computação e da Informação - Ciências Naturais