Governmental institutions are employing artificial intelligence techniques to deal with their specific problems and exploit their huge amounts of both structured and unstructured information. In particular, natural language processing and machine learning techniques are being used to process citizen feedback. In this paper, we report on the use of such techniques for analyzing and classifying complaints, in the context of the Portuguese Economic and Food Safety Authority. Grounded in its operational process, we address three different classification problems: target economic activity, implied infraction severity level, and institutional competence. We show promising results obtained using feature-based approaches and traditional classifiers, with accuracy scores above 70%, and analyze the shortcomings of our current results and avenues for further improvement, taking into account the intended use of our classifiers in helping human officers to cope with thousands of yearly complaints.
This paper describes our participation in the message polarity classification task of SemEval 2014. We focused on exploiting unlabeled data to improve accuracy, combining features leveraging word representations with other, more common features, based on word tokens or lexicons. We analyse the contribution of the different features, concluding that unlabeled data yields significant improvements.
Abstract. Information related to mobility dynamics constitutes an important factor to be considered in traffic management to improve the efficiency of existing systems. We present a proof-of-concept deployment of sensors using the Bluetooth technology to detect traffic flow conditions. Besides traditional method consisting of a network of stationary sensors, we present a novel approach that uses sensors deployed in moving vehicles. Both approaches complement the most common methods of traffic sensing while being more cost-effective and easily available. Early experimental results show the variety of information available through both approaches from Origin/Destination matrices to travel times and insights into mobility neighborhoods. These matrices are important to improve traffic management increasing the efficiency of urban mobility networks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.