Over time, the use of Machine Learning tools has become a great method to build actionable insights. The action of studying the people interactions through social networks and Natural Language Processing is a great example on how opinions about certain topics can be retrieved and analyzed. Sustainable mobility is a growing concern in our modern society and it’s important to research how people react to new policies regarding this topic. In order to so, a dashboard to track sustainable mobility social trends has been developed. This project is aligned with the United Nations’ sustainable development goal number 11, which promotes sustainable cities and communities. To achieve this, tweets are analyzed to be categorized, detect named entities and provide the sentiment of Twitter messages. The pipeline that processes the data has been created using Big Data technologies: Luigi to orchestrate the different processes, the Python scientific ecosystem to analyze data and evaluate models, and ElasticSearch for storing the generated data. To analyze the polarity of Twitter messages (positive, negative, neutral), a deep learning sentiment analysis model has been created, trained, and thoroughly evaluated. Once the input data is semantically enriched, a dynamic dashboard, created using Polymer, provides a comprehensive visualization of the retrieved data alongside different charts to aggregate the analyzed information.