Sentiment in Citizen Feedback: Exploration by Supervised Learning

Robin Lybeck, Samuel Rönnqvist, Sampo Ruoppila

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review


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.

Original languageUndefined/Unknown
Title of host publicationProceedings of the International Conference EGOV-CeDEM-ePart 2018
EditorsShefali Virkar, Peter Parycek, Noella Edelmann, Olivier Glassey, Marijn Janssen, Hans Jochen Scholl, Efthimios Tambouris
PublisherEdition Donau-Universität Krems
ISBN (Print)9783903150225
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventEGOV-CeDEM-ePart - EGOV-CeDEM-ePart 2018
Duration: 3 Sept 20185 Sept 2018



Cite this