The CSBNO project aimed to understand the needs and expectations of the community for digital services during a period of crisis. Two sentiment analysis and topic detection algorithms were applied to the datasets collected by librarians with the transcription of phone calls to library users. The results showed an interest in the digital library even though the print book is preferred, with positive sentiments for the services of MLOL and OPAC. The project is proposed as an example of conducting community surveys, using algorithms for the analysis of the sentiments and that can be reused in the future in different circumstances.