Sentiment in Citizen Feedback: Exploration by Supervised Learning

Web-based citizen feedback systems have become commonplace in cities around theworld, resulting in vast amounts of data. Recent advances in machine learning and naturallanguage processing enable novel and practical ways of analysing it as big data. This paperreports an explorative case study of sentiment analysis of citizen feedback (in Finnish) bymeans of annotation with custom categories (Positive, Neutral, Negative, Angry, Constructiveand Unsafe) and predictive modelling. We analyse the results quantitatively and qualitatively,illustrate the benefits of such an approach, and discuss the use of machine learning in thecontext of studying citizen feedback. Custom annotation is a laborious process, but it offerstask-specific adaptation and enables empirically grounded analysis. In this study, annotationwas carried out at a moderate scale. The resulting model performed well in the most frequentcategories, while the infrequent ones remained a challenge. Nonetheless, this kind of approachhas promising features for developing automated systems of processing textual citizenfeedback.